def follow_object(objectID, centroid, totalUp, totalDown):
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid)
else:
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
if not to.counted:
if direction < 0 and centroid[0] < W // 4:
totalUp += 1
to.counted = True
elif direction > 0 and centroid[0] > W // 4:
totalDown += 1
to.counted = True
trackableObjects[objectID] = to
return totalUp, totalDown
def assosciate_tracked_objects(self, rects, ct, frame, H, W, writer):
objects = ct.update(rects)
for (objectID, centroid) in objects.items():
to = self.trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
else:
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
if not to.counted:
if direction < 0:
self.countExit += 1
to.counted = True
elif direction > 0:
self.countEnter += 1
to.counted = True
self.trackableObjects[objectID] = to
# Display the count of people entered & exited the store/frame.
info = [
("# Exited", self.countExit),
("# Entered", self.countEnter),
]
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (W - 170, (i * 20) + 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
# Bounding boxes on the tracked detections
for rect in rects:
(startX, startY, endX, endY) = rect
cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 0, 255),
2)
if writer is not None:
writer.write(frame)
self.totalFrames += 1
def processVideo(prototxt, model, filepath):
print("[INFO] Filepath: " + filepath)
print("[INFO] model: " + model)
print("[INFO] prototxt: " + prototxt)
outputPath = "./userapp/output.avi"
skipframes = 30
conf = 0.4
# construct the argument parse and parse the arguments
# ap = argparse.ArgumentParser()
# ap.add_argument(prototxt)
# ap.add_argument(model)
# ap.add_argument(filepath)
# # ap.add_argument("-o", "--output", type=str,
# # help="path to optional output video file")
# ap.add_argument("-c", "--confidence", type=float, default=0.4,
# help="minimum probability to filter weak detections")
# ap.add_argument("-s", "--skip-frames", type=int, default=30,
# help="# of skip frames between detections")
# args = vars(ap.parse_args())
# print("[INFO] Starting2.....")
# initialize the list of class labels MobileNet SSD was trained to
# detect
CLASSES = [
"background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus",
"car", "cat", "chair", "cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant", "sheep", "sofa", "train",
"tvmonitor"
]
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(prototxt, model)
# if a video path was not supplied, grab a reference to the webcam
# if not args.get("input", False):
# print("[INFO] starting video stream...")
# vs = VideoStream(src=0).start()
# time.sleep(2.0)
# otherwise, grab a reference to the video file
# else:
# print("[INFO] opening video file...")
# vs = cv2.VideoCapture(args["input"])
vs = cv2.VideoCapture(filepath)
# initialize the video writer (we'll instantiate later if need be)
writer = None
# initialize the frame dimensions (we'll set them as soon as we read
# the first frame from the video)
W = None
H = None
# instantiate our centroid tracker, then initialize a list to store
# each of our dlib correlation trackers, followed by a dictionary to
# map each unique object ID to a TrackableObject
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
trackers = []
trackableObjects = {}
# initialize the total number of frames processed thus far, along
# with the total number of objects that have moved either up or down
totalFrames = 0
totalDown = 0
totalUp = 0
# start the frames per second throughput estimator
fps = FPS().start()
# loop over frames from the video stream
while True:
# grab the next frame and handle if we are reading from either
# VideoCapture or VideoStream
print("[Info] Filepath is" + filepath)
frame = vs.read()
frame = frame[1] if filepath else frame
# if we are viewing a video and we did not grab a frame then we
# have reached the end of the video
if filepath is not None and frame is None:
break
# resize the frame to have a maximum width of 500 pixels (the
# less data we have, the faster we can process it), then convert
# the frame from BGR to RGB for dlib
frame = imutils.resize(frame, width=500)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# if the frame dimensions are empty, set them
if W is None or H is None:
(H, W) = frame.shape[:2]
# if we are supposed to be writing a video to disk, initialize
# the writer
if outputPath is not None and writer is None:
print("[INFO] loading model...after vs1")
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
print("[INFO] loading model...after vs2 :" + outputPath)
writer = cv2.VideoWriter(outputPath, fourcc, 30, (W, H), True)
print("[INFO] loading model...after vs3")
# initialize the current status along with our list of bounding
# box rectangles returned by either (1) our object detector or
# (2) the correlation trackers
status = "Waiting"
print("[INFO] loading model...after vs")
rects = []
print("[INFO] loading model...after cv2")
# check to see if we should run a more computationally expensive
# object detection method to aid our tracker
if totalFrames % skipframes == 0:
# set the status and initialize our new set of object trackers
status = "Detecting"
trackers = []
# convert the frame to a blob and pass the blob through the
# network and obtain the detections
blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated
# with the prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by requiring a minimum
# confidence
if confidence > conf:
# extract the index of the class label from the
# detections list
idx = int(detections[0, 0, i, 1])
# if the class label is not a person, ignore it
if CLASSES[idx] != "person":
continue
# compute the (x, y)-coordinates of the bounding box
# for the object
box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
(startX, startY, endX, endY) = box.astype("int")
# construct a dlib rectangle object from the bounding
# box coordinates and then start the dlib correlation
# tracker
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(startX, startY, endX, endY)
tracker.start_track(rgb, rect)
# add the tracker to our list of trackers so we can
# utilize it during skip frames
trackers.append(tracker)
# otherwise, we should utilize our object *trackers* rather than
# object *detectors* to obtain a higher frame processing throughput
else:
# loop over the trackers
for tracker in trackers:
# set the status of our system to be 'tracking' rather
# than 'waiting' or 'detecting'
status = "Tracking"
# update the tracker and grab the updated position
tracker.update(rgb)
pos = tracker.get_position()
# unpack the position object
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
# add the bounding box coordinates to the rectangles list
rects.append((startX, startY, endX, endY))
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
cv2.line(frame, (0, H // 2), (W, H // 2), (0, 255, 255), 2)
# use the centroid tracker to associate the (1) old object
# centroids with (2) the newly computed object centroids
objects = ct.update(rects)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
to.counted = True
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
elif direction > 0 and centroid[1] > H // 2:
totalDown += 1
to.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# draw both the ID of the object and the centroid of the
# object on the output frame
text = "ID {}".format(objectID)
cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
# construct a tuple of information we will be displaying on the
# frame
info = [
("Up", totalUp),
("Down", totalDown),
("Status", status),
]
# loop over the info tuples and draw them on our frame
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
# check to see if we should write the frame to disk
if writer is not None:
writer.write(frame)
# show the output frame
# cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# increment the total number of frames processed thus far and
# then update the FPS counter
totalFrames += 1
fps.update()
# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# check to see if we need to release the video writer pointer
if writer is not None:
writer.release()
print("[INFO] Total Up Count: " + str(totalUp))
# if we are not using a video file, stop the camera video stream
# if filepath is not None:
# vs.stop()
# # otherwise, release the video file pointer
# else:
# vs.release()
# close any open windows
cv2.destroyAllWindows()
# only proceed if the radius meets a minimum size
if radius > args["radius"]:
# draw the circle and centroid on the frame,
# then update the list of tracked points
cv2.circle(frame, (int(x), int(y)), int(radius), (0, 255, 255),
2)
cv2.circle(frame, center[-1], 5, (0, 0, 255), -1)
rects.append((x - radius, y - radius, x + radius, y + radius))
# use centroidtracker to associate detected objects with objects in previous frame
objects = ct.update(rects)
# use trackable object to plot object trail
for (objectID, centroid) in objects.items():
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid, args["buffer"])
to.deque.appendleft(centroid)
else:
to.centroids.append(centroid)
to.deque.appendleft(centroid)
trackableObjects[objectID] = to
for j in range(1, len(to.deque)):
if to.deque[j - 1] is None or to.deque[j] is None:
continue
thickness = int(np.sqrt(args["buffer"] / float(j + 1)) * 2.5)
cv2.line(frame, (to.deque[j - 1][0], to.deque[j - 1][1]),
(to.deque[j][0], to.deque[j][1]), (0, 0, 255),
thickness)
# show the frame to our screen
cv2.imshow("Frame", frame)
up_arrowpt = (W // 2, H // 2 - 30)
center_pt2 = (W // 2, H // 2 + 8)
down_arrowpt = (W // 2, H // 2 + 30)
cv2.arrowedLine(frame, center_pt1, up_arrowpt, (0,0,255), 2)
cv2.arrowedLine(frame, center_pt2, down_arrowpt, (255,0,0), 2)
objects = ct.update(rects)
for (objectID, centroid) in objects.items():
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid)
else:
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
if not to.counted:
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
to.directiontext = "(up)"
to.counted = True
elif direction > 0 and centroid[1] > H // 2:
def processor(img, h, w):
global tracker_list
global max_detection
global min_detection
global track_id_list
global sum_unmatched_dets
global totalDown
global totalUp
global id_counter
global n_frame
global horizontal
global tracker_dict
#declare either horizontal or vertical line for pedestrian countings
if horizontal == True:
loi = h
coord = 1
else:
loi = w
coord = 0
n_frame = n_frame + 1
# get the detections bounding boxes
# get_localization function runs the tf detection
z_box_raw = det.get_localization(img)
z_box = z_box_raw[0]
output_dict = z_box_raw[1]
# initiate the tracker list
x_box = []
if len(tracker_list) > 0:
for trk in tracker_list:
# add tracking boxes from the previous frames
# it updates constantly unmatched tracks eventually deleted
x_box.append(trk.box)
# call the function
matched, unmatched_dets, unmatched_trks = assign_detections_to_trackers(
x_box, z_box, iou_thrd=0.3)
# calculate the total number of objetcs appeared in the footage (roughly)
# considering each unmatched_det is the new object appeared in the frame
# matched detections
# not entering this part from the beginning (matched size is 0 at first run)
if matched.size > 0:
for det_idx, trk_idx in matched:
# extract the boxes of matched detected objects only
z = z_box[det_idx]
z = np.expand_dims(z, axis=0).T
# extract the boxes of matched tracked objects only
tmp_trk = tracker_list[trk_idx]
# Apply kalman filter with update part
tmp_trk.kalman_filter(z)
# extract bounding boxes XX
xx = tmp_trk.x_state.T[0].tolist()
# extract positions only (up, left, down, right)
xx = [xx[0], xx[2], xx[4], xx[6]]
# write KF output box to the tracked boxes array
x_box[trk_idx] = xx
tmp_trk.box = xx
# number of detection matches
tmp_trk.hits += 1
# unmatched detections
# the code enters this part first because first detections are unmatched by default (no tracking values)
if len(unmatched_dets) > 0:
# loop over unmatched detections
for idx in unmatched_dets:
z = z_box[idx]
z = np.expand_dims(z, axis=0).T
# call the object "Tracker"
tmp_trk = tracking_layer.Tracker() # new tracker
# create array with the bounding boxes locations and the velocities
# velocity is set to 0 if the detection is not matched
x = np.array([[z[0], 0, z[1], 0, z[2], 0, z[3], 0]]).T
# assign the state array for Kalman filter
tmp_trk.x_state = x
# predict thfe tracking boxes and velocities using predict_only
# function different from KF (no update part)
tmp_trk.predict_only()
# write the predicted values into XX variable
xx = tmp_trk.x_state
# Transpose the array
xx = xx.T[0].tolist()
# extract the locations only (uo, left, down, right)
xx = [xx[0], xx[2], xx[4], xx[6]]
# list to store the coordinates for a bounding box
tmp_trk.box = xx
# assign the ID to the tracked box
tmp_trk.id = id_counter
id_counter = id_counter + 1
# add the tracking box into the tracker list (in the binary form for cv2 draw)
tracker_list.append(tmp_trk)
# add the tracking box into the tracker list (in the integer form)
x_box.append(xx)
# unmatched tracks
# this tracks are not stored into tracker_list so not drawn on the image
if len(unmatched_trks) > 0:
for trk_idx in unmatched_trks:
tmp_trk = tracker_list[trk_idx]
# add a number of unmatched tracks (track loss)
tmp_trk.no_losses += 1
# function different from KF (no update part)
# these values are not using for the further computations so can bde deleted
tmp_trk.predict_only()
xx = tmp_trk.x_state
xx = xx.T[0].tolist()
xx = [xx[0], xx[2], xx[4], xx[6]]
tmp_trk.box = xx
x_box[trk_idx] = xx
good_tracker_list = []
# loop over all tracked list
for trk in tracker_list:
# if within a constraint
if ((trk.hits >= min_detection) and (trk.no_losses <= max_detection)):
good_tracker_list.append(trk)
x_cv2 = trk.box
#convert boxes to their centroid values
center = convert_boxes_to_centroids(x_cv2)
#append object ID as keys and centers as values to the dictionary
tracker_dict.setdefault(trk.id, []).append(center)
#draw the box on frame
img = tracking_utils.draw_box_label(trk.id, img, x_cv2)
#update tracks every 100 frames
# if n_frame == 25:
# with open(PATH_TO_SAVE_TRACKS+'/'+output_tracks_name + '.json', 'w') as fp:
# json.dump(tracker_dict, fp)
# n_frame = 0;
#iterate through the dictionary
for (objectID, center) in tracker_dict.items():
#check if ObjectID is in the trackableObjects class
check = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if check is None:
check = TrackableObject(objectID, center)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* 5 centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down') We need its length to be more than 5
#x = [c[1] for c in check.center]
if len(center) > 5:
check.center.append(center)
mean_value = (center[-5][coord] + center[-4][coord] +
center[-3][coord] + center[-2][coord] +
center[-1][coord]) / 5
direction = center[-1][coord] - mean_value
# check to see if the object has been counted or not
if not check.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the check
# line AND the mean of the previous values is below the line, count the object
# Mean of the previous values needs to be checked so prevent objects which are already below the line
# and moving to the negative direction to be counted
if direction < 0 and center[-1][
coord] < loi / 2 and mean_value > loi / 2:
totalUp += 1
check.counted = True
# same logic but for the positive direction
elif direction > 0 and center[-1][
coord] > loi / 2 and mean_value < loi / 2:
totalDown += 1
check.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = check
# draw the line and put text on the frame
if horizontal == True:
cv2.line(img, (0, int(loi / 2)), (w, int(loi / 2)), (0, 0xFF, 0),
5)
else:
cv2.line(img, (int(loi / 2), 0), (int(loi / 2), h), (0, 0xFF, 0),
5)
cv2.putText(
img, 'Up ' + str(totalUp) + ' Down ' + str(totalDown) +
' Total ' + str(totalUp + totalDown), (10, 35),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 0), 2,
cv2.FONT_HERSHEY_SIMPLEX)
print('Total number of people crossed ' + str(totalUp + totalDown))
tracker_list = [x for x in tracker_list if x.no_losses <= max_detection]
return img, output_dict
def Stream():
st.title("Customer Tracker")
st.text(
"This application will track how many customer enter & exit your premise"
)
st.markdown("\n", unsafe_allow_html=True)
camera = st.text_input("Enter Camera/Webcam Path")
col1, col2 = st.beta_columns(2)
if col1.button('Start ▶️') and not col2.button("Stop ⏹️"):
if camera.isnumeric():
camera = int(camera)
st.info("Live Streaming")
elif camera is not None:
st.error("Please Enter the Correct Camera Path")
image_placeholder = st.empty()
#confidenceValue = 0.4
#frameValue = 30
# initialize the list of class labels MobileNet SSD was trained to
# detect
CLASSES = [
"background", "aeroplane", "bicycle", "bird", "boat", "bottle",
"bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant", "sheep", "sofa", "train",
"tvmonitor"
]
# load our serialized model from disk
net = cv2.dnn.readNetFromCaffe("MobileNetSSD_deploy.prototxt",
"MobileNetSSD_deploy.caffemodel")
print("[INFO] Starting the video..")
vs = cv2.VideoCapture(camera)
# initialize the frame dimensions (we'll set them as soon as we read
# the first frame from the video)
W = None
H = None
# instantiate our centroid tracker, then initialize a list to store
# each of our dlib correlation trackers, followed by a dictionary to
# map each unique object ID to a TrackableObject
ct = CentroidTracker(maxDisappeared=80, maxDistance=50)
trackers = []
trackableObjects = {}
# initialize the total number of frames processed thus far, along
# with the total number of objects that have moved either up or down
totalFrames = 0
totalDown = 0
totalUp = 0
x = []
empty = []
empty1 = []
# start the frames per second throughput estimator
fps = FPS().start()
# loop over frames from the video stream
while True:
# grab the next frame and handle if we are reading from either
ret, frame = vs.read()
# resize the frame to have a maximum width of 500 pixels (the
# less data we have, the faster we can process it), then convert
# the frame from BGR to RGB for dlib
frame = imutils.resize(frame, width=700) # Default width = 500
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# if the frame dimensions are empty, set them
if W is None or H is None:
(H, W) = frame.shape[:2]
# initialize the current status along with our list of bounding
# box rectangles returned by either (1) our object detector or
# (2) the correlation trackers
status = "Waiting"
rects = []
# check to see if we should run a more computationally expensive
# object detection method to aid our tracker
if totalFrames % 30 == 0:
# set the status and initialize our new set of object trackers
status = "Detecting"
trackers = []
# convert the frame to a blob and pass the blob through the
# network and obtain the detections
blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated
# with the prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by requiring a minimum
# confidence
if confidence > 0.4:
# extract the index of the class label from the
# detections list
idx = int(detections[0, 0, i, 1])
# if the class label is not a person, ignore it
if CLASSES[idx] != "person":
continue
# compute the (x, y)-coordinates of the bounding box
# for the object
box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
(startX, startY, endX, endY) = box.astype("int")
# construct a dlib rectangle object from the bounding
# box coordinates and then start the dlib correlation
# tracker
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(startX, startY, endX, endY)
tracker.start_track(rgb, rect)
# add the tracker to our list of trackers so we can
# utilize it during skip frames
trackers.append(tracker)
# otherwise, we should utilize our object *trackers* rather than
# object *detectors* to obtain a higher frame processing throughput
else:
# loop over the trackers
for tracker in trackers:
# set the status of our system to be 'tracking' rather
# than 'waiting' or 'detecting'
status = "Tracking"
# update the tracker and grab the updated position
tracker.update(rgb)
pos = tracker.get_position()
# unpack the position object
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
# add the bounding box coordinates to the rectangles list
rects.append((startX, startY, endX, endY))
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
cv2.line(frame, (0, H // 2), (W, H // 2), (0, 0, 255), 3)
cv2.putText(frame, "Prediction border", (10, H - ((i * 20) + 200)),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
# use the centroid tracker to associate the (1) old object
# centroids with (2) the newly computed object centroids
objects = ct.update(rects)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
empty.append(totalUp)
to.counted = True
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
elif direction > 0 and centroid[1] > H // 2:
totalDown += 1
empty1.append(totalDown)
#print(empty1[-1])
x = []
# compute the sum of total people inside
x.append(len(empty1) - len(empty))
#print("Total people inside:", x)
# if the people limit exceeds over threshold, send an email alert
if sum(x) >= config.Threshold:
cv2.putText(frame,
"-ALERT: People limit exceeded-",
(10, frame.shape[0] - 80),
cv2.FONT_HERSHEY_COMPLEX, 0.5,
(0, 0, 255), 2)
if config.ALERT:
print("[INFO] Sending email alert..")
Mailer().send(config.MAIL)
print("[INFO] Alert sent")
to.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# draw both the ID of the object and the centroid of the
# object on the output frame
text = "ID {}".format(objectID)
cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
cv2.circle(frame, (centroid[0], centroid[1]), 4,
(255, 255, 255), -1)
# construct a tuple of information we will be displaying on the
info = [
("Exit", totalUp),
("Enter", totalDown),
("Status", status),
]
info2 = [
("Total people inside", x),
]
# Display the output
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 250), 2)
for (i, (k, v)) in enumerate(info2):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (265, H - ((i * 20) + 60)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
#Logs.csv
# Initiate a simple log to save data at end of the day
# if config.Log:
# datetimee = [datetime.datetime.now()]
# d = [datetimee, empty1, empty, x]
# export_data = zip_longest(*d, fillvalue = '')
# with open('Log.csv', 'w', newline='') as myfile:
# wr = csv.writer(myfile, quoting=csv.QUOTE_ALL)
# wr.writerow(("End Time", "In", "Out", "Total Inside"))
# wr.writerows(export_data)
#cv2.imshow("Real-Time Monitoring/Analysis Window", frame)
# show the output frame
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image_placeholder.image(frame)
#key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
#if key == ord("q"):
# break
# increment the total number of frames processed thus far and
# then update the FPS counter
totalFrames += 1
fps.update()
if config.Timer:
# Automatic timer to stop the live stream. Set to 8 hours (28800s).
t1 = time.time()
num_seconds = (t1 - t0)
if num_seconds > 28800:
break
# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# # if we are not using a video file, stop the camera video stream
# if not args.get("input", False):
# vs.stop()
#
# # otherwise, release the video file pointer
# else:
# vs.release()
# close any open windows
cv2.destroyAllWindows()
def evaluate(stream=None):
mixer.init()
mixer.music.load('support/alert.wav')
playing = False
args = dict(
prototxt='support/model.prototxt',
model='support/model.caffemodel',
input=stream,
output=None,
confidence=0.4,
skip_frames=30)
# initialize the list of class labels MobileNet SSD was trained to
# detect
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# if a video path was not supplied, grab a reference to the webcam
if not args.get("input", False):
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
time.sleep(2.0)
# otherwise, grab a reference to the video file
else:
print("[INFO] opening video file...")
vs = cv2.VideoCapture(args["input"])
# initialize the video writer (we'll instantiate later if need be)
writer = None
# initialize the frame dimensions (we'll set them as soon as we read
# the first frame from the video)
W = None
H = None
# instantiate our centroid tracker, then initialize a list to store
# each of our dlib correlation trackers, followed by a dictionary to
# map each unique object ID to a TrackableObject
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
trackers = []
trackableObjects = {}
# initialize the total number of frames processed thus far, along
# with the total number of objects that have moved either up or down
totalFrames = 0
total = 0
# start the frames per second throughput estimator
fps = FPS().start()
# loop over frames from the video stream
while True:
# grab the next frame and handle if we are reading from either
# VideoCapture or VideoStream
frame = vs.read()
frame = frame[1] if args.get("input", False) else frame
# if we are viewing a video and we did not grab a frame then we
# have reached the end of the video
if args["input"] is not None and frame is None:
break
# resize the frame to have a maximum width of 500 pixels (the
# less data we have, the faster we can process it), then convert
# the frame from BGR to RGB for dlib
frame = imutils.resize(frame, width=500)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# if the frame dimensions are empty, set them
if W is None or H is None:
(H, W) = frame.shape[:2]
# if we are supposed to be writing a video to disk, initialize
# the writer
if args["output"] is not None and writer is None:
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
writer = cv2.VideoWriter(args["output"], fourcc, 30,
(W, H), True)
# initialize the current status along with our list of bounding
# box rectangles returned by either (1) our object detector or
# (2) the correlation trackers
status = "Waiting"
rects = []
# check to see if we should run a more computationally expensive
# object detection method to aid our tracker
if totalFrames % args["skip_frames"] == 0:
# set the status and initialize our new set of object trackers
status = "Detecting"
trackers = []
# convert the frame to a blob and pass the blob through the
# network and obtain the detections
blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated
# with the prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by requiring a minimum
# confidence
if confidence > args["confidence"]:
# extract the index of the class label from the
# detections list
idx = int(detections[0, 0, i, 1])
# if the class label is not a person, ignore it
if CLASSES[idx] != "person":
continue
# compute the (x, y)-coordinates of the bounding box
# for the object
box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
(startX, startY, endX, endY) = box.astype("int")
# construct a dlib rectangle object from the bounding
# box coordinates and then start the dlib correlation
# tracker
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(startX, startY, endX, endY)
tracker.start_track(rgb, rect)
# add the tracker to our list of trackers so we can
# utilize it during skip frames
trackers.append(tracker)
# otherwise, we should utilize our object *trackers* rather than
# object *detectors* to obtain a higher frame processing throughput
else:
# loop over the trackers
for tracker in trackers:
# set the status of our system to be 'tracking' rather
# than 'waiting' or 'detecting'
status = "Tracking"
# update the tracker and grab the updated position
tracker.update(rgb)
pos = tracker.get_position()
# unpack the position object
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
# add the bounding box coordinates to the rectangles list
rects.append((startX, startY, endX, endY))
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
# cv2.line(frame, (0, H // 2), (W, H // 2), (0, 255, 255), 2)
# use the centroid tracker to associate the (1) old object
# centroids with (2) the newly computed object centroids
objects = ct.update(rects)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[1] < H // 2:
total += 1
to.counted = True
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
elif direction > 0 and centroid[1] > H // 2:
total += 1
to.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# draw both the ID of the object and the centroid of the
# object on the output frame
text = "ID {}".format(objectID)
cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
corona_danger_count = 0
current_id_centroid = []
for (objectID, centroid) in objects.items():
current_id_centroid.append(centroid)
t = np.array(current_id_centroid)
already_played = []
if(t.ndim == 2):
D = dist.cdist(current_id_centroid, current_id_centroid,metric ="euclidean")
(row,col) = D.shape
for i in range(row):
for j in range(col):
if(i==j):
continue
if(D[i][j]< 120):
corona_danger_count+=1
cv2.circle(frame,(current_id_centroid[i][0],current_id_centroid[i][1]), 8, (0, 0 , 255), -1)
danger = "DANGER"
if(mixer.music.get_busy() or (i,j) in already_played):
pass
else:
mixer.music.play()
already_played.append((i,j))
already_played.append((j,i))
cv2.putText(frame, danger, (current_id_centroid[i][0] - 10, current_id_centroid[i][1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 3)
# construct a tuple of information we will be displaying on the
# frame
info = [
("Distinguishable Objects", total),
("Voilation Count", corona_danger_count),
("Status", status),
]
# loop over the info tuples and draw them on our frame
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 2)
# check to see if we should write the frame to disk
if writer is not None:
writer.write(frame)
# show the output frame
cv2.imshow("Social Distancing Enforcer", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# increment the total number of frames processed thus far and
# then update the FPS counter
totalFrames += 1
fps.update()
# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# check to see if we need to release the video writer pointer
if writer is not None:
writer.release()
# if we are not using a video file, stop the camera video stream
if not args.get("input", False):
vs.stop()
# otherwise, release the video file pointer
else:
vs.release()
# close any open windows
cv2.destroyAllWindows()
def main():
global payload
# argument parsing
parser = argparse.ArgumentParser()
parser.add_argument('--headless',
help='run the pygame headlessly',
action='store_true')
parser.add_argument("--color_depth",
help="integer number of colors to use to draw temps",
type=int)
parser.add_argument('--max_temp', help='initial max temperature', type=int)
parser.add_argument(
'--ambient_offset',
help='value to offset ambient temperature by to get rolling MAXTEMP',
type=int)
parser.add_argument(
'--ambient_time',
help='length of ambient temperature collecting intervals in seconds',
type=int)
parser.add_argument('--blob_min_threshold',
help='blod detection min threshold',
type=int)
parser.add_argument('--blob_max_threshold',
help='blod detection min threshold',
type=int)
parser.add_argument('--blob_filterbyarea',
help='blod detection filter by area',
action='store_true')
parser.add_argument('--blob_min_area',
help='blod detection filter by area min area',
type=int)
parser.add_argument('--blob_filterbycircularity',
help='blod detection filter by circularity',
action='store_true')
parser.add_argument(
'--blob_min_circularity',
help='blod detection filter by circularity min circularity',
type=float)
parser.add_argument('--blob_filterbyconvexity',
help='blod detection filter by convexity',
action='store_true')
parser.add_argument(
'--blob_min_convexity',
help='blod detection filter by convexity min convexity',
type=float)
parser.add_argument('--blob_filterbyinertia',
help='blod detection filter by inertia',
action='store_true')
parser.add_argument('--blob_min_inertiaratio',
help='blod detection filter by inertia inertia ratio',
type=float)
parser.add_argument(
'--mysql_send_interval',
help='length of intervals between attempted mysql insert in seconds',
type=int)
args = parser.parse_args()
print(args)
i2c_bus = busio.I2C(board.SCL, board.SDA)
COLOR_DEPTH = args.color_depth
MAX_TEMP = args.max_temp
AMBIENT_OFFSET = args.ambient_offset
AMBIENT_TIME = args.ambient_time
BLOB_MIN_THRESHOLD = args.blob_min_threshold
BLOB_MAX_THRESHOLD = args.blob_max_threshold
BLOB_FILTERBYAREA = args.blob_filterbyarea
BLOB_MIN_AREA = args.blob_min_area
BLOB_FILTERBYCIRCULARITY = args.blob_filterbycircularity
BLOB_MIN_CIRCULARITY = args.blob_min_circularity
BLOB_FILTERBYCONVEXITY = args.blob_filterbyconvexity
BLOB_MIN_CONVEXITY = args.blob_min_convexity
BLOB_FILTERBYINERTIA = args.blob_filterbyinertia
BLOB_MIN_INERTIARATIO = args.blob_min_inertiaratio
MYSQL_SEND_INTERVAL = args.mysql_send_interval
if args.headless:
os.putenv('SDL_VIDEODRIVER', 'dummy')
else:
os.putenv('SDL_FBDEV', '/dev/fb1')
pygame.init()
# initialize the sensor
sensor = adafruit_amg88xx.AMG88XX(i2c_bus)
points = [(math.floor(ix / 8), (ix % 8)) for ix in range(0, 64)]
grid_x, grid_y = np.mgrid[0:7:32j, 0:7:32j]
# sensor is an 8x8 grid so lets do a square
height = 240
width = 240
# the list of colors we can choose from
black = Color("black")
colors = list(black.range_to(Color("white"), COLOR_DEPTH))
# create the array of colors
colors = [(int(c.red * 255), int(c.green * 255), int(c.blue * 255))
for c in colors]
displayPixelWidth = width / 30
displayPixelHeight = height / 30
lcd = pygame.display.set_mode((width, height))
lcd.fill((255, 0, 0))
pygame.display.update()
pygame.mouse.set_visible(False)
lcd.fill((0, 0, 0))
pygame.display.update()
# Setup SimpleBlobDetector parameters.
params = cv2.SimpleBlobDetector_Params()
# Change thresholds
if BLOB_MIN_THRESHOLD:
params.minThreshold = BLOB_MIN_THRESHOLD
if BLOB_MAX_THRESHOLD:
params.maxThreshold = BLOB_MAX_THRESHOLD
# Filter by Area.
if BLOB_FILTERBYAREA:
params.filterByArea = BLOB_FILTERBYAREA
params.minArea = BLOB_MIN_AREA
# Filter by Circularity
if BLOB_FILTERBYCIRCULARITY:
params.filterByCircularity = BLOB_FILTERBYCIRCULARITY
params.minCircularity = BLOB_MIN_CIRCULARITY
# Filter by Convexity
if BLOB_FILTERBYCONVEXITY:
params.filterByConvexity = BLOB_FILTERBYCONVEXITY
params.minConvexity = BLOB_MIN_CONVEXITY
# Filter by Inertia
if BLOB_FILTERBYINERTIA:
params.filterByInertia = BLOB_FILTERBYINERTIA
params.minInertiaRatio = BLOB_MIN_INERTIARATIO
# Set up the detector with default parameters.
detector = cv2.SimpleBlobDetector_create(params)
# initialize centroid tracker
ct = CentroidTracker()
# a dictionary to map each unique object ID to a TrackableObject
trackableObjects = {}
# the total number of objects that have moved either up or down
total_down = 0
total_up = 0
total_down_old = 0
total_up_old = 0
# let the sensor initialize
time.sleep(.1)
# press key to exit
screencap = True
# array to hold mode of last 10 minutes of temperatures
mode_list = []
send_thread = threading.Thread(target=send_mysql,
args=(MYSQL_SEND_INTERVAL, ))
send_thread.start()
print('sensor started!')
while (screencap):
start = time.time()
# read the pixels
pixels = []
for row in sensor.pixels:
pixels = pixels + row
payload['a'] = 0
payload['o'] = 0
payload['c'] = ct.get_count()
mode_result = stats.mode([round(p) for p in pixels])
mode_list.append(int(mode_result[0]))
# instead of taking the ambient temperature over one frame of data take it over a set amount of time
MAX_TEMP = float(np.mean(mode_list)) + AMBIENT_OFFSET
pixels = [
map_value(p, mode_result[0] + 1, MAX_TEMP, 0, COLOR_DEPTH - 1)
for p in pixels
]
# perform interpolation
bicubic = griddata(points, pixels, (grid_x, grid_y), method='cubic')
# draw everything
for ix, row in enumerate(bicubic):
for jx, pixel in enumerate(row):
try:
pygame.draw.rect(
lcd, colors[constrain(int(pixel), 0, COLOR_DEPTH - 1)],
(displayPixelHeight * ix, displayPixelWidth * jx,
displayPixelHeight, displayPixelWidth))
except:
print("Caught drawing error")
surface = pygame.display.get_surface()
myfont = pygame.font.SysFont("comicsansms", 25)
img = pygame.surfarray.array3d(surface)
img = np.swapaxes(img, 0, 1)
# Read image
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = cv2.bitwise_not(img)
# Detect blobs.
keypoints = detector.detect(img)
img_with_keypoints = cv2.drawKeypoints(
img, keypoints, np.array([]), (0, 0, 255),
cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
pygame.draw.line(lcd, (255, 255, 255), (0, height // 2),
(width, height // 2), 2)
pygame.display.update()
for i in range(0, len(keypoints)):
x = keypoints[i].pt[0]
y = keypoints[i].pt[1]
# print circle around blobs
pygame.draw.circle(lcd, (200, 0, 0), (int(x), int(y)),
round(keypoints[i].size), 2)
# update our centroid tracker using the detected centroids
objects = ct.update(keypoints)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
# the historical centroid must present in the lower half of the screen
if direction < 0 and centroid[
1] < height // 2 and count_within_range(
y, height // 2, height) > 0:
total_up += 1
to.counted = True
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
# the historical centroid must present in the upper half of the screen
elif direction > 0 and centroid[
1] > height // 2 and count_within_range(
y, 0, height // 2) > 0:
total_down += 1
to.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# update counter in top left
textsurface1 = myfont.render("IN: " + str(total_up), False,
(255, 255, 255))
textsurface2 = myfont.render('OUT: ' + str(total_down), False,
(255, 255, 255))
lcd.blit(textsurface1, (0, 0))
lcd.blit(textsurface2, (0, 25))
total_up_old = total_up
total_down_old = total_down
pygame.display.update()
for event in pygame.event.get():
if event.type == pygame.KEYDOWN:
print('terminating...')
screencap = False
break
# for running the save on for a certain amount of time
# if time.time() - start_time >= 10:
# print('terminating...')
# screencap = False
# empty mode_list every AMBIENT_TIME *10 seconds to get current ambient temperature
if len(mode_list) > AMBIENT_TIME:
mode_list = []
time.sleep(max(1. / 25 - (time.time() - start), 0))
# Release everything if job is finished
cv2.destroyAllWindows()
def main():
# argument parsing
parser = argparse.ArgumentParser()
parser.add_argument('--headless',
help='run the pygame headlessly',
action='store_true')
parser.add_argument("--color_depth",
help="integer number of colors to use to draw temps",
type=int)
parser.add_argument('--max_temp', help='initial max temperature', type=int)
parser.add_argument(
'--ambient_offset',
help='value to offset ambient temperature by to get rolling MAXTEMP',
type=int)
parser.add_argument(
'--ambient_time',
help='length of ambient temperature collecting intervals in seconds',
type=int)
parser.add_argument('--blob_min_threshold',
help='blod detection min threshold',
type=int)
parser.add_argument('--blob_max_threshold',
help='blod detection min threshold',
type=int)
parser.add_argument('--blob_filterbyarea',
help='blod detection filter by area',
action='store_true')
parser.add_argument('--blob_min_area',
help='blod detection filter by area min area',
type=int)
parser.add_argument('--blob_filterbycircularity',
help='blod detection filter by circularity',
action='store_true')
parser.add_argument(
'--blob_min_circularity',
help='blod detection filter by circularity min circularity',
type=float)
parser.add_argument('--blob_filterbyconvexity',
help='blod detection filter by convexity',
action='store_true')
parser.add_argument(
'--blob_min_convexity',
help='blod detection filter by convexity min convexity',
type=float)
parser.add_argument('--blob_filterbyinertia',
help='blod detection filter by inertia',
action='store_true')
parser.add_argument('--blob_min_inertiaratio',
help='blod detection filter by inertia inertia ratio',
type=float)
args = parser.parse_args()
print(args)
COLOR_DEPTH = args.color_depth
MAX_TEMP = args.max_temp
AMBIENT_OFFSET = args.ambient_offset
AMBIENT_TIME = args.ambient_time
BLOB_MIN_THRESHOLD = args.blob_min_threshold
BLOB_MAX_THRESHOLD = args.blob_max_threshold
BLOB_FILTERBYAREA = args.blob_filterbyarea
BLOB_MIN_AREA = args.blob_min_area
BLOB_FILTERBYCIRCULARITY = args.blob_filterbycircularity
BLOB_MIN_CIRCULARITY = args.blob_min_circularity
BLOB_FILTERBYCONVEXITY = args.blob_filterbyconvexity
BLOB_MIN_CONVEXITY = args.blob_min_convexity
BLOB_FILTERBYINERTIA = args.blob_filterbyinertia
BLOB_MIN_INERTIARATIO = args.blob_min_inertiaratio
# create data folders if they don't exist
if not os.path.exists(get_filepath('../img')):
os.makedirs(get_filepath('../img'))
if not os.path.exists(get_filepath('../data')):
os.makedirs(get_filepath('../data'))
if not os.path.exists(get_filepath('../video')):
os.makedirs(get_filepath('../video'))
# empty the images folder
for filename in os.listdir(get_filepath('../img/')):
if filename.endswith('.jpeg'):
os.unlink(get_filepath('../img/') + filename)
i2c_bus = busio.I2C(board.SCL, board.SDA)
# For headless pygame
if args.headless:
os.putenv('SDL_VIDEODRIVER', 'dummy')
else:
os.putenv('SDL_FBDEV', '/dev/fb1')
pygame.init()
# initialize the sensor
sensor = adafruit_amg88xx.AMG88XX(i2c_bus)
points = [(math.floor(ix / 8), (ix % 8)) for ix in range(0, 64)]
grid_x, grid_y = np.mgrid[0:7:32j, 0:7:32j]
# sensor is an 8x8 grid so lets do a square
height = 240
width = 240
# the list of colors we can choose from
black = Color("black")
colors = list(black.range_to(Color("white"), COLOR_DEPTH))
# create the array of colors
colors = [(int(c.red * 255), int(c.green * 255), int(c.blue * 255))
for c in colors]
displayPixelWidth = width / 30
displayPixelHeight = height / 30
lcd = pygame.display.set_mode((width, height))
lcd.fill((255, 0, 0))
pygame.display.update()
pygame.mouse.set_visible(False)
lcd.fill((0, 0, 0))
pygame.display.update()
# Setup SimpleBlobDetector parameters.
params = cv2.SimpleBlobDetector_Params()
# Change thresholds
if BLOB_MIN_THRESHOLD:
params.minThreshold = BLOB_MIN_THRESHOLD
if BLOB_MAX_THRESHOLD:
params.maxThreshold = BLOB_MAX_THRESHOLD
# Filter by Area.
if BLOB_FILTERBYAREA:
params.filterByArea = BLOB_FILTERBYAREA
params.minArea = BLOB_MIN_AREA
# Filter by Circularity
if BLOB_FILTERBYCIRCULARITY:
params.filterByCircularity = BLOB_FILTERBYCIRCULARITY
params.minCircularity = BLOB_MIN_CIRCULARITY
# Filter by Convexity
if BLOB_FILTERBYCONVEXITY:
params.filterByConvexity = BLOB_FILTERBYCONVEXITY
params.minConvexity = BLOB_MIN_CONVEXITY
# Filter by Inertia
if BLOB_FILTERBYINERTIA:
params.filterByInertia = BLOB_FILTERBYINERTIA
params.minInertiaRatio = BLOB_MIN_INERTIARATIO
# Set up the detector with default parameters.
detector = cv2.SimpleBlobDetector_create(params)
# initialize centroid tracker
ct = CentroidTracker()
# a dictionary to map each unique object ID to a TrackableObject
trackableObjects = {}
# the total number of objects that have moved either up or down
total_down = 0
total_up = 0
total_down_old = 0
total_up_old = 0
# let the sensor initialize
time.sleep(.1)
# press key to exit
screencap = True
# json dump
data = {}
data['sensor_readings'] = []
# array to hold mode of last 10 minutes of temperatures
mode_list = []
print('sensor started!')
start_time = time.time()
while (screencap):
start = time.time()
date = datetime.now()
# read the pixels
pixels = []
for row in sensor.pixels:
pixels = pixels + row
data['sensor_readings'].append({
'time': datetime.now().isoformat(),
'temps': pixels,
'count': ct.get_count()
})
mode_result = stats.mode([round(p) for p in pixels])
mode_list.append(int(mode_result[0]))
# instead of taking the ambient temperature over one frame of data take it over a set amount of time
MAX_TEMP = float(np.mean(mode_list)) + AMBIENT_OFFSET
pixels = [
map_value(p,
np.mean(mode_list) + 1, MAX_TEMP, 0, COLOR_DEPTH - 1)
for p in pixels
]
# perform interpolation
bicubic = griddata(points, pixels, (grid_x, grid_y), method='cubic')
# draw everything
for ix, row in enumerate(bicubic):
for jx, pixel in enumerate(row):
try:
pygame.draw.rect(
lcd, colors[constrain(int(pixel), 0, COLOR_DEPTH - 1)],
(displayPixelHeight * ix, displayPixelWidth * jx,
displayPixelHeight, displayPixelWidth))
except:
print("Caught drawing error")
surface = pygame.display.get_surface()
myfont = pygame.font.SysFont("comicsansms", 25)
# frame saving
folder = get_filepath('../img/')
filename = str(date) + '.jpeg'
#pygame.image.save(surface, folder + filename)
img = pygame.surfarray.array3d(surface)
img = np.swapaxes(img, 0, 1)
# Read image
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_not = cv2.bitwise_not(img)
# Detect blobs.
keypoints = detector.detect(img_not)
img_with_keypoints = cv2.drawKeypoints(
img, keypoints, np.array([]), (0, 0, 255),
cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
# draw a horizontal line in the center of the frame -- once an
# object crosses this line we will determine whether they were
# moving 'up' or 'down'
pygame.draw.line(lcd, (255, 255, 255), (0, height // 2),
(width, height // 2), 2)
pygame.display.update()
for i in range(0, len(keypoints)):
x = keypoints[i].pt[0]
y = keypoints[i].pt[1]
# print circle around blob
pygame.draw.circle(lcd, (200, 0, 0), (int(x), int(y)),
round(keypoints[i].size), 2)
# update our centroid tracker using the detected centroids
objects = ct.update(keypoints)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[
1] < height // 2 and count_within_range(
y, height // 2, height) > 0:
total_up += 1
to.counted = True
# if the direction is positive (indicating the object
# is moving down) AND the centroid is below the
# center line, count the object
elif direction > 0 and centroid[
1] > height // 2 and count_within_range(
y, 0, height // 2) > 0:
total_down += 1
to.counted = True
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# update counter in top left
textsurface1 = myfont.render("IN: " + str(total_up), False,
(255, 255, 255))
textsurface2 = myfont.render('OUT: ' + str(total_down), False,
(255, 255, 255))
lcd.blit(textsurface1, (0, 0))
lcd.blit(textsurface2, (0, 25))
total_up_old = total_up
total_down_old = total_down
pygame.display.update()
pygame.image.save(surface, folder + filename)
for event in pygame.event.get():
if event.type == pygame.KEYDOWN:
print('terminating...')
screencap = False
break
# for running the save on for a certain amount of time
# if time.time() - start_time >= 10:
# print('terminating...')
# screencap = False
# empty mode_list every AMBIENT_TIME seconds
if len(mode_list) > AMBIENT_TIME:
mode_list = []
time.sleep(max(1. / 25 - (time.time() - start), 0))
# write raw sensor data to file
data_index = 0
while os.path.exists(
get_filepath('../data/') + 'data%s.json' % data_index):
data_index += 1
data_path = str(get_filepath('../data/') + 'data%s.json' % data_index)
with open(data_path, 'w+') as outfile:
json.dump(data, outfile, indent=4)
# stitch the frames together
dir_path = get_filepath('../img/')
ext = '.jpeg'
out_index = 0
while os.path.exists(
get_filepath('../video/') + 'output%s.avi' % out_index):
out_index += 1
output = str(get_filepath('../video/') + 'output%s.avi' % out_index)
framerate = 10
# get files from directory
images = []
for f in os.listdir(dir_path):
if f.endswith(ext):
images.append(f)
# sort files
images = sorted(images,
key=lambda x: datetime.strptime(
x.split('.j')[0], '%Y-%m-%d %H:%M:%S.%f'))
# determine width and height from first image
image_path = os.path.join(dir_path, images[0])
frame = cv2.imread(image_path)
if not args.headless:
cv2.imshow('video', frame)
height, width, channels = frame.shape
# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'XVID') # Be sure to use lower case
out = cv2.VideoWriter(output, fourcc, framerate, (width, height))
for image in images:
image_path = os.path.join(dir_path, image)
frame = cv2.imread(image_path)
out.write(frame) # Write out frame to video
if not args.headless:
cv2.imshow('video', frame)
if (cv2.waitKey(1) & 0xFF) == ord('q'): # Hit `q` to exit
break
print('video created!')
# Release everything if job is finished
out.release()
cv2.destroyAllWindows()
def detect_temp(self):
self.face_detector.start()
res = libuvc.uvc_start_streaming(self.devh, byref(self.ctrl),
PTR_PY_FRAME_CALLBACK, None, 0)
if res < 0:
print("uvc_start_streaming failed: {0}".format(res))
trackableObjects = {}
# loop over frames from the video stream
while _THREADING["shouldrun"]:
detector_ready = self.face_detector.isstarted()
# grab frame from each camera
data = q.get(True, 500)
if data is None or not detector_ready:
time.sleep(1.0)
continue
data = cv2.resize(data[:, :], (400, 300))
raw_data = data.copy()
lepton_frame = raw_to_8bit(data)
lepton_frame = cv2.flip(lepton_frame, 1)
# use the centroid tracker to associate the (1) old object
# centroids with (2) the newly computed object centroids
objects = self.face_detector.objects.copy()
obj_rects = self.face_detector.obj_rects.copy()
# loop over the tracked objects
for (objectID, centroid) in objects.items():
# check to see if a trackable object exists for the current
# object ID
to = trackableObjects.get(objectID, None)
# compute max temp for ROI
(startX, startY, endX, endY) = obj_rects[objectID]
if startX < 0:
startX = 0
if startY < 0:
startY = 0
if endX > 400:
endX = 400
if endY > 300:
endY = 300
max_temp = np.max(raw_data[startY:endY, startX:endX])
val = ktoc(max_temp)
temp = "Max {0:.1f} degC".format(val)
color = (0, 255, 0)
if self.low_temp < val < self.high_temp:
color = (0, 255, 255)
elif val >= 37:
color = (0, 0, 255)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
# otherwise, there is a trackable object so we can utilize it
# to determine direction
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids will tell
# us in which direction the object is moving (negative for
# 'up' and positive for 'down')
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# store the trackable object in our dictionary
trackableObjects[objectID] = to
# draw both the ID of the object and the centroid of the
# object on the output frame
text = "ID {}".format(objectID)
#cv2.putText(lepton_frame, text, (centroid[0] - 10, centroid[1] - 10),
# cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
cv2.circle(lepton_frame, (centroid[0], centroid[1]), 4, color,
-1)
cv2.rectangle(lepton_frame, (startX, startY), (endX, endY),
color, 2)
cv2.putText(lepton_frame, temp, (startX, startY - 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 0), 2)
#Determine if face close enough to temp camera (improve reading accuracy)
iou = self.bb_intersection_over_union(
self.TEMP_BBOX, [startX, startY, endX, endY])
if iou > 0.5:
self.temperature = "{0:.1f}".format(val)
# show the output frame
# draw temperature reading box
lepton_frame = cv2.rectangle(
lepton_frame, (self.CROP_X, self.CROP_Y),
(self.CROP_X + self.SIZE, self.CROP_Y + self.SIZE),
(255, 255, 255), 2)
lepton_frame = cv2.resize(lepton_frame, (800, 600),
interpolation=cv2.INTER_LINEAR)
self.thermal_frame = lepton_frame
def counting_vehicle(input_path, output_path, model_cfg, name_list,
model_weight, skip_frame, thresh_prop, horizon):
'''
Parameters:
+ video_path:
. None: take frame from camera
. path: take frame from video
+ output_path:
. None: show the result
. path: save into new video
+ name_list: list labels
+ model_cfg: model config
+ model_weight: model weight
+ skip_frame: number of frame that system take sample 1 time
+ thresh_prop: the minimum score (propability) accepted to recognize an object
Output: None
+ horizon = the number decide line system counting on
'''
if input_path == None:
print("Starting streaming")
cap = cv2.VideoCapture(0)
time.sleep(2.0)
else:
print("Opening " + input_path)
cap = cv2.VideoCapture(input_path)
if output_path != None:
writer = None
config = model_cfg
weight = model_weight
name = name_list
with open(name, 'r') as f:
# generate all classes of COCO, bicycle idx = 1, car idx = 2 and motorbike idx = 3
classes = [line.strip() for line in f.readlines()]
np.random.seed(11)
COLORS = np.random.uniform(0, 255, size=(len(classes), 3))
# Read the model
net = cv2.dnn.readNet(weight, config)
# take shape of image in order to scale it to 416x416, first layer of Yolo CNN
scale = 0.00392
W = None
H = None
ct = CentroidTracker(maxDisappeared=20, maxDistance=30)
# trackers = []
trackableObjects = {}
totalFrames = 0
totalDown = 0
totalUp = 0
while True:
ret,frame = cap.read()
# Resize width to 500 and scale height propability equal
# 500/old_width (because the smaller pics the faster our model run)
frame = imutils.resize(frame, width = 500)
# convert to rgb for dlib
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if W is None or H is None:
# take original for scale the output of YOLO
(H,W) = frame.shape[:2]
status = "Waiting"
rects = []
# release memory
if totalFrames == skip_frame**3:
totalFrames = 1
if totalFrames % skip_frame == 0:
status = "Detecting"
trackers = []
blob = cv2.dnn.blobFromImage(frame, scale, (416, 416), (0,0,0), True, crop =False)
net.setInput(blob)
outs = net.foward(get_output_layers(net))
for out in outs:
for detection in out:
scores = detection[5:]
# get the highest score to determine its label
class_id = np.argmax(scores)
# make sure we only choose vehicle
if class_id not in [0,1,2,3,7]:
continue
else:
# score of that object, make sure more than 50% correct label
confidence = scores[class_id]
if confidence > thresh_prop:
center_x = int(detection[0] * Width)
center_y = int(detection[1] * Height)
w = int(detection[2] * Width)
h = int(detection[3] * Height)
# remember it return x_center and y_center, not x,y, so we need to find x,y
x = center_x - w / 2
y = center_y - h / 2
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(x, y, x+w, y+h)
tracker.start_track(rgb, rect)
trackers.append(tracker)
else:
for tracker in tracks:
status = "Tracking"
tracker.update(rgb)
pos = tracker.get_position()
# unpack the position object
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
rects.append((startX, startY, endX, endY))
cv2.line(frame, (0, horizon), (W, horizon), (0, 255, 255), 2)
objects = ct.update(rects)
for (objectID, centroid) in objects.items():
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid)
else:
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has been counted or not
if not to.counted:
# if the direction is negative (indicating the object
# is moving up) AND the centroid is above the center
# line, count the object
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
to.counted = True
elif direction > 0 and centroid[1] > H // 2:
totalDown += 1
to.counted = True
trackableObjects[objectID] = to
text = "ID {}".format(objectID)
cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
info = [
("Up", totalUp),
("Down", totalDown),
("Status", status),
]
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
def run():
classes = [c.strip() for c in open('coco.names').readlines()]
conf_threshold = 0.6 # lay confidence > 0.5
nmsThreshold = 0.4 # > 0.5 se ap dung Non-max Surpression
shape = 288
colors = []
colors.append([(randint(0, 255), randint(0, 255), randint(0, 255))
for i in range(1000)])
detected_classes = ['cell phone']
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
pts = [deque(maxlen=10) for _ in range(1000)]
counter = 0
center = None
trackers = []
totalIn = []
empty = []
empty1 = []
trackableObjects = {}
totalFrames = 0
totalDown = 0
totalUp = 0
(W, H) = (None, None)
net = yolo_net("yolov3.weights", "yolov3.cfg")
if config.Thread:
vid = thread.ThreadingClass(0)
else:
vid = cv2.VideoCapture(0)
while True:
if config.Thread:
img = vid.read()
else:
_, img = vid.read()
img = cv2.resize(img, (600, 500))
rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
if W is None or H is None:
(H, W) = img.shape[:2]
status = "Waiting"
rects = []
if totalFrames % 30 == 0:
status = "Detecting"
trackers = []
outputs = yolo_output(net, img, shape)
bbox, classIds, confs = yolo_predict(outputs, conf_threshold, H, W)
indices = cv2.dnn.NMSBoxes(bbox, confs, conf_threshold,
nmsThreshold)
for i in indices:
i = i[0]
if classes[classIds[i]] not in detected_classes: continue
box = bbox[i]
color = colors[0][i]
x, y, w, h = box[0], box[1], box[2], box[3]
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(x, y, x + w, y + h)
tracker.start_track(rgb, rect)
trackers.append(tracker)
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
else:
for tracker in trackers:
status = "Tracking"
tracker.update(rgb)
pos = tracker.get_position()
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
rects.append((startX, startY, endX, endY))
cv2.line(img, (0, H // 2), (W, H // 2), (0, 255, 255), 2)
obj = ct.update(rects)
for (objectID, centroid) in obj.items():
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid)
else:
oy = [c[1] for c in to.centroids]
directionY = centroid[1] - np.mean(oy)
to.centroids.append(centroid)
if not to.counted:
if directionY < 0 and centroid[1] < H // 2:
totalUp += 1
empty.append(totalUp)
to.counted = True
elif directionY > 0 and centroid[1] > H // 2:
totalDown += 1
empty1.append(totalDown)
# print(empty1[-1])
totalIn = []
# compute the sum of total people inside
totalIn.append(len(empty1) - len(empty))
print("Total people inside:", totalIn)
# if the people limit exceeds over threshold, send an email alert
if sum(totalIn) >= config.Threshold:
cv2.putText(img, "-ALERT: People limit exceeded-",
(10, img.shape[0] - 80),
cv2.FONT_HERSHEY_COMPLEX, 0.5,
(0, 0, 255), 2)
if config.ALERT:
print("[INFO] Sending email alert..")
# Mailer().send(config.MAIL)
print("[INFO] Alert sent")
to.counted = True
trackableObjects[objectID] = to
text1 = "ID {}".format(objectID)
colorID = colors[0][objectID]
cv2.circle(img, (centroid[0], centroid[1]), 4, colorID, -1)
# cv2.putText(img, "Direction: {}".format(direction), (10, 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
center = (centroid[0], centroid[1])
pts[objectID].append(center)
for i in range(1, len(pts[objectID])):
if pts[objectID][i - 1] is None or pts[objectID][i] is None:
continue
thickness = int(np.sqrt(10 / float(i + 1)) * 2.5)
cv2.line(img, pts[objectID][i - 1], pts[objectID][i], colorID,
thickness)
info = [
("Up", totalUp),
("Down", totalDown),
("Status", status),
]
info2 = [
("Total people inside", totalIn),
]
for (i, (k, v)) in enumerate(info):
text2 = "{}: {}".format(k, v)
cv2.putText(img, text2, (10, H - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
for (i, (k, v)) in enumerate(info2):
text3 = "{}: {}".format(k, v)
cv2.putText(img, text3, (265, H - ((i * 20) + 60)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
if config.Log:
datetimee = [
datetime.datetime.now().strftime("%d/%m/%Y, %H:%M:%S")
]
d = [datetimee, empty1, empty, totalIn]
print("D: ", d)
export_data = zip_longest(*d, fillvalue='')
print("Export Data: ", export_data)
with open('Log.csv', 'w', newline='') as myfile:
wr = csv.writer(myfile, quoting=csv.QUOTE_ALL)
wr.writerow(("End Time", "In", "Out", "Total Inside"))
wr.writerows(export_data)
myfile.close()
with open('Log.csv', 'a', newline='') as f:
wr = csv.writer(f, quoting=csv.QUOTE_ALL)
wr.writerows(export_data)
cv2.imshow('Result', img)
key = cv2.waitKey(1)
if key == ord('q'): break
totalFrames += 1
if config.Timer:
# Automatic timer to stop the live stream. Set to 8 hours (28800s).
t1 = time.time()
num_seconds = (t1 - t0)
if num_seconds > 28800:
break
if not config.Thread:
vid.release()
cv2.destroyAllWindows()
def age_gender(vs,dur):
totalFrames = 0
totalDown = 0
totalUp = 0
rects=[]
agen = []
gend = []
writer = None
W= None
H= None
up = []
down = []
skipFrames = rate
status = ""
net = cv2.dnn.readNet("deploy.prototxt", "deploy.caffemodel")
age_net = cv2.dnn.readNetFromCaffe('deploy_age.prototxt', 'age_net.caffemodel')
gender_net = cv2.dnn.readNetFromCaffe('deploy_gender.prototxt', 'gender_net.caffemodel')
font = cv2.FONT_HERSHEY_SIMPLEX
MODEL_MEAN_VALUES = (78.4263377603, 87.7689143744, 114.895847746)
age_list = ['(0, 2)', '(4, 6)', '(8, 12)', '(15, 20)', '(25, 32)', '(38, 43)', '(48, 53)', '(60, 100)']
gender_list = ['Male', 'Female']
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
frameST = st.empty()
trackers = []
trackableObjects = {}
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
widgets = ['Loading: ', progressbar.AnimatedMarker()]
bar = progressbar.ProgressBar(widgets=widgets).start()
with st.spinner('Processing...'):
while True:
frame = vs.read()
frame = frame[1]
if frame is None:
break
frame = imutils.resize(frame, width=320)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if W is None or H is None:
(H, W) = frame.shape[:2]
status = "Waiting"
rects = []
if totalFrames % skipFrames < skipFrames/5:
status = "Detecting"
trackers = []
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_alt.xml')
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.1, 5)
for (x, y, w, h )in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 255, 0), 2)
face_img = frame[y:y+h, h:h+w].copy()
blob = cv2.dnn.blobFromImage(face_img, 1, (227, 227), MODEL_MEAN_VALUES, swapRB=False)
gender_net.setInput(blob)
gender_preds = gender_net.forward()
gender = gender_list[gender_preds[0].argmax()]
print("Gender : " + gender)
age_net.setInput(blob)
age_preds = age_net.forward()
age = age_list[age_preds[0].argmax()]
print("Age Range: " + age)
overlay_text = "%s %s" % (gender, age)
cv2.putText(frame, overlay_text, (x, y), font, 1, (255, 255, 255), 2, cv2.LINE_AA)
agen.append(age)
gend.append(gender)
blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
net.setInput(blob)
detections = net.forward()
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > confidence_threshold:
idx = int(detections[0, 0, i, 1])
if CLASSES[idx] not in ("person"):
continue
box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
(startX, startY, endX, endY) = box.astype("int")
tracker = dlib.correlation_tracker()
rect = dlib.rectangle(startX, startY, endX, endY)
tracker.start_track(rgb, rect)
trackers.append(tracker)
else:
for tracker in trackers:
status = "Tracking"
tracker.update(rgb)
pos = tracker.get_position()
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
rects.append((startX, startY, endX, endY))
cv2.line(frame, (0, 0), (W, 0), (0, 255, 255), 2)
objects = ct.update(rects)
for (objectID, centroid) in objects.items():
to = trackableObjects.get(objectID, None)
if to is None:
to = TrackableObject(objectID, centroid)
else:
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
if not to.counted:
if direction < 0 and centroid[1] < H // 2:
totalUp += 1
to.counted = True
elif direction > 0 and centroid[1] > H // 2:
totalDown += 1
to.counted = True
up.append(totalUp)
down.append(totalDown)
trackableObjects[objectID] = to
text = "ID {}".format(objectID)
cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
info = [("Up", totalUp),("Down", totalDown),("Status", status),]
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(frame, text, (10, H - ((i * 20) + 20)),cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
totalFrames += 1
frameST.image(frame, channels="BGR",caption='output video', use_column_width=True)
if writer is None:
fourcc = cv2.VideoWriter_fourcc(*"XVID")
writer = cv2.VideoWriter("output.avi", fourcc, rate,(frame.shape[1], frame.shape[0]), True)
return up, down, gend, agen
def sm_update(self):
print("Entered state update")
cv2.line(self.frame, (0, self.height // 2),
(self.width, self.height // 2), (0, 255, 255), 2)
objects = self.ct.update(self.rects)
# loop over the tracked objects
for (objectID, centroid) in objects.items():
to = self.trackableObjects.get(objectID, None)
# if there is no existing trackable object, create one
if to is None:
to = TrackableObject(objectID, centroid)
else:
# the difference between the y-coordinate of the *current*
# centroid and the mean of *previous* centroids give the
# in which direction the object is moving
y = [c[1] for c in to.centroids]
direction = centroid[1] - np.mean(y)
to.centroids.append(centroid)
# check to see if the object has already been counted
if not to.counted:
# direction is negative(moving up)
# AND centroid is above centre, count the obect
if direction < 0 and centroid[1] < self.height // 2:
self.Up += 1
to.counted = True
# direction is positive(moving down)
# AND centroid is below centre, count the obect
elif direction > 0 and centroid[1] > self.height // 2:
self.Down += 1
to.counted = True
# store the trackable object
# trackableObjects[objectID] = to
# get count of people inside
self.peopleInside = self.Down - self.Up
self.trackableObjects[objectID] = to
text = "ID {}".format(objectID)
cv2.putText(self.frame, text, (centroid[0] - 10, centroid[1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
cv2.circle(self.frame, (centroid[0], centroid[1]), 4, (0, 255, 0),
-1)
# for rect in self.rects:
# (startX, startY, endX, endY) = rect
# cv2.rectangle(self.frame, (startX, startY), (endX, endY),
# (0, 255, 0), 2)
info = [
("People inside", self.peopleInside),
("Tracker", self.selected_tracker),
]
for (i, (k, v)) in enumerate(info):
text = "{}: {}".format(k, v)
cv2.putText(self.frame, text, (10, self.height - ((i * 20) + 20)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
if self.writer is not None:
self.writer.write(self.frame)
cv2.imshow("Frame", self.frame)
key = cv2.waitKey(1) & 0xFF
if key == 27: # Escape
self.processing_videotofinalize_video.emit()
if key == ord('s'):
currentDate = datetime.now()
date = datetime.strftime(currentDate, "%m%d%H%M")
photoname = os.path.join("results", "captura_" + date + ".jpg")
print("[SAVING]", photoname)
cv2.imwrite(photoname, self.frame)
self.totalFrames += 1
self.fps.update()
self.updatetoreading_frames.emit()