def _main_(args):
# Set up device
device = mvnc.Device(args['device'])
device.open()
fifoIn, fifoOut = graph.allocate_with_fifos(device, graphfile)
# Configuration stuff needed for postprocessing the predictions
config_path = args['config']
with open(config_path) as config_buffer:
config = json.load(config_buffer)
backend = config['model']['backend']
input_size = (config['model']['input_size_h'],config['model']['input_size_w'])
labels = config['model']['labels']
max_box_per_image = config['model']['max_box_per_image']
anchors = config['model']['anchors']
gray_mode = config['model']['gray_mode']
nb_class = 1
# Predict bounding boxes
if video_mode:
cap = FileVideoStream(source).start()
time.sleep(1.0)
fps = FPS().start()
fps_img = 0.0
counter = 0
while True:
start = time.time()
image = cap.read()
# Preprocessing
if depth == 1:
# convert video to gray
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = cv2.resize(image, input_size, interpolation = cv2.INTER_CUBIC)
image = np.expand_dims(image, 2)
fimage = np.array(image, dtype=np.float32)
else:
image = cv2.resize(image, input_size, interpolation = cv2.INTER_CUBIC)
fimage = np.array(image, dtype=np.float32)
#image = np.expand_dims(image, 0)
fimage = np.divide(fimage, 255.)
tm_inf = time.time()
graph.queue_inference_with_fifo_elem(fifoIn, fifoOut, fimage, 'user object')
prediction, _ = fifoOut.read_elem()
#prediction = np.add(fimage, 128)
grid = 8
prediction = np.reshape(prediction, (grid, grid, 5, 4 + 1 + nb_class))
# prediction = np.multiply(prediction, 255)
fps_img = ( fps_img + ( 1 / (time.time() - start) ) ) / 2
print( "Inference time: {:.4f}".format(time.time() - tm_inf) )
# predictions decoding
boxes = decode_netout(prediction, anchors, nb_class)
image = draw_boxes(image, boxes, config['model']['labels'])
image = cv2.putText(image, "fps: {:.2f}".format(fps_img), (0, 20), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 0), 1, 4 )
cv2.imshow("Press q to quit", image)
fps.update()
#if counter == 10:
#print(image.sum(), boxes)
# time.sleep(1)
counter += 1
if cv2.getWindowProperty( "Press q to quit", cv2.WND_PROP_ASPECT_RATIO ) < 0.0:
print("Window closed" )
break
elif cv2.waitKey( 1 ) & 0xFF == ord( 'q' ):
print( "Q pressed" )
break
fps.stop()
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
cap.release()
else:
#detected_images_path = os.path.join(image_path, "detected")
#if not os.path.exists(detected_images_path):
# os.mkdir(detected_images_path)
images = list(list_images(source))
for fname in images[100:]:
image = cv2.imread(fname)
tm_inf = time.time()
boxes = yolo.predict(image)
print( "Inference time: {:.4f}".format(time.time() - tm_inf) )
image = draw_boxes(image, boxes, config['model']['labels'])
cv2.imshow("Press q to quit", image)
if cv2.waitKey( 1 ) & 0xFF == ord( 'q' ):
break
time.sleep(2)
# fname = os.path.basename(fname)
# cv2.imwrite(os.path.join(image_path, "detected", fname), image)
cv2.destroyAllWindows()
class VideoCamera(object):
def __init__(self):
# Using OpenCV to capture from device 0. If you have trouble capturing
# from a webcam, comment the line below out and use a video file
# instead.
# self.video = cv2.VideoCapture(0)
# If you decide to use video.mp4, you must have this file in the folder
# as the main.py.
self.video = FileVideoStream("cropvideo.mp4").start()
def __del__(self):
self.video.release()
def get_frame(self):
image = self.video.read()
faceCascade = cv2.CascadeClassifier('haarcascade_profileface.xml')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(gray, 1.1, 4)
# We are using Motion JPEG, but OpenCV defaults to capture raw images,
# so we must encode it into JPEG in order to correctly display the
# video stream.
for (x, y, w, h) in faces:
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
ret, jpeg = cv2.imencode('.jpg', image)
return jpeg.tobytes()
class CustomStream:
def __init__(self, src=0, use_cv2=False):
if use_cv2:
self.obj = cv2.VideoCapture(src)
elif src == 0:
self.obj = WebcamVideoStream(src)
elif src != 0:
self.obj = FileVideoStream(src)
def isOpened(self):
if isinstance(self.obj, cv2.VideoCapture):
return self.obj.isOpened()
return self.obj.stream.isOpened()
def start(self):
self.obj.start()
return self
def update(self):
self.obj.update()
def read(self):
if isinstance(self.obj, cv2.VideoCapture):
return self.obj.read()
return not self.obj.stopped, self.obj.read()
def stop(self):
self.obj.stop()
if isinstance(self.obj, cv2.VideoCapture):
self.obj.release()
else:
self.obj.stream.release()
def set(self, propId, value):
if isinstance(self.obj, cv2.VideoCapture):
self.obj.set(propId, value)
return
self.obj.stream.set(propId, value)
def get(self, propId):
if isinstance(self.obj, cv2.VideoCapture):
self.obj.get(propId)
return
return self.obj.stream.get(propId)
def recognise_face(data,input,args):
# initialize the pointer to the video file and the video writer
print("[INFO] processing video...")
stream = cv2.VideoCapture(args["input"])
stream = FileVideoStream(args["input"]).start()
# fps =FPS(args["input"])#.start()
# stream =fps
writer = None
# loop over frames from the video file stream
while stream.more():
# grab the next frame
frame = stream.read()
# if the frame was not grabbed, then we have reached the
# end of the stream
# if not grabbed:
# break
# convert the input frame from BGR to RGB then resize it to have
# a width of 750px (to speedup processing)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
rgb = imutils.resize(frame, width=750)
r = frame.shape[1] / float(rgb.shape[1])
# detect the (x, y)-coordinates of the bounding boxes
# corresponding to each face in the input frame, then compute
# the facial embeddings for each face
boxes = face_recognition.face_locations(frame,
model=args["detection_method"])
encodings = face_recognition.face_encodings(rgb, boxes)
names = []
results =[]
# loop over the facial embeddings
for encoding in encodings:
# attempt to match each face in the input image to our known
# encodings
matches = face_recognition.compare_faces(data["encodings"],
encoding)
name = "Unknown_0"
# check to see if we have found a match
if True in matches:
# find the indexes of all matched faces then initialize a
# dictionary to count the total number of times each face
# was matched
matchedIdxs = [i for (i, b) in enumerate(matches) if b]
counts = {}
# loop over the matched indexes and maintain a count for
# each recognized face face
for i in matchedIdxs:
name = data["names"][i]
key = str(name) + "_" +str(data["id"][i])
counts[key] = counts.get(key, 0) + 1
# determine the recognized face with the largest number
# of votes (note: in the event of an unlikely tie Python
# will select first entry in the dictionary)
name = max(counts, key=counts.get)
# update the list of names, id
name = name.split("_")
id = int(name[-1])
name = name[:-1]
name = " ".join(name)
names.append(name)
results.append(dict(id=id, name=name))
# loop over the recognized faces
for ((top, right, bottom, left), name,res) in zip(boxes, names,results):
# rescale the face coordinates
top = int(top * r)
right = int(right * r)
bottom = int(bottom * r)
left = int(left * r)
# draw the predicted face name on the image
cv2.rectangle(frame, (left, top), (right, bottom),
(0, 255, 0), 2)
y = top - 15 if top - 15 > 15 else top + 15
cv2.putText(frame, name, (left, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
yield res
# if the video writer is None *AND* we are supposed to write
# the output video to disk initialize the writer
if writer is None and args["output"] is not None:
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
writer = cv2.VideoWriter(args["output"], fourcc, 24,
(frame.shape[1], frame.shape[0]), True)
# if the writer is not None, write the frame with recognized
# faces t odisk
if writer is not None:
writer.write(frame)
# check to see if we are supposed to display the output frame to
# the screen
if args["display"] > 0:
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# close the video file pointers
stream.release()
# check to see if the video writer point needs to be released
if writer is not None:
writer.release()
# draw the total number of social distancing violations on the
# output frame
text = "Social Distancing Violations: {}".format(len(violate))
cv2.putText(frame, text, (10, frame.shape[0] - 25),
cv2.FONT_HERSHEY_SIMPLEX, 0.85, (0, 0, 255), 3)
######################################################
# show the output frame
cv2.imshow("Frame", frame)
fps.update()
#for i in range(50000000):
# pass
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# update the FPS counte
# 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()))
# do a bit of cleanup
cv2.destroyAllWindows()
vs.release()
(h, w) = frame.shape[:2]
# blob = cv2.dnn.blobFromImage(image, scalefactor=1.0, size, mean, swapRB=True)
blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0,
(300, 300), (104.7, 177.0, 123.0), True)
net.setInput(blob)
detections = net.forward()
for i in range(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence < args["confidence"]:
continue
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
text = "{:.2f}%".format(confidence * 100)
y = startY - 10 if startY - 10 > 10 else startY + 10
cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 255, 255), 2)
cv2.putText(frame, text, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.45,
(0, 0, 255), 2)
cv2.imshow("Frame", frame)
cv2.waitKey(1)
vs.update()
vs.stop()
fvs.release()
cv2.destroyAllWindows()
class IP(object):
def __init__(self):
#self.cap = cv2.VideoCapture(1)
self.fvs = FileVideoStream(1)
# self.fvs.stream.set(3,FULL_WIDTH)
# self.fvs.stream.set(4,FULL_HEIGHT)
self.fvs.start()
#self.fvs = FileVideoStream(0).start
# self.cap.set(3,FULL_WIDTH) #3 - WIDTH
# self.cap.set(4,FULL_HEIGHT) #4 - HEIGHT
def get_image(self):
#ret,image = self.cap.read()
# print image
image = self.fvs.read()
i = 0
#image = np.dstack([image, image, image])
#print ("SHAPE : ",image.shape)
image = imutils.resize(image, width=FULL_WIDTH) #,height=FULL_HEIGHT)
print("SHAPE : ", image.shape)
# while not np.size(image,0) == FULL_HEIGHT or not np.size(image,1) == FULL_WIDTH :
# print ("trying",i)
# print ("SHAPE : ",image.shape)
# i += 1
# image = self.fvs.read()
# #ret,image = self.cap.read()
return image
def perspective_transform(self, image, pts1, pts2):
return cv2.warpPerspective(image,
cv2.getPerspectiveTransform(pts1, pts2),
(FINAL_WIDTH, FINAL_HEIGHT))
def rgb2gray(self, image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
def rgb2hsv(self, image):
return cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
def threshold_image(self, image, threshold, max_val):
return cv2.threshold(image, threshold, max_val, cv2.THRESH_BINARY)
def display_image(self, image, window_name="Image"):
cv2.imshow(window_name, image)
if cv2.waitKey(1) == ord('q'):
cv2.destroyAllWindows()
self.fvs.stop()
return 0
return 1
def find_contours(self, image):
major, _, _ = cv2.__version__.split('.')
if major == '3':
_, contour, hierarchy = cv2.findContours(image, cv2.RETR_TREE, 2)
else:
contour, hierarchy = cv2.findContours(image, cv2.RETR_TREE, 2)
return contour, hierarchy
def find_area(self, contour):
return cv2.contourArea(contour)
def find_moments(self, contour):
return cv2.moments(contour)
def crop_image(self, image, center, amount):
#print int(center[1])-amount,int(center[0])-amount
#print int(center[1])+amount,int(center[0])+amount
if int(center[1]) - amount >= 0 and int(center[0]) - amount >= 0:
if int(center[1]) + amount <= FINAL_HEIGHT and int(
center[0]) + amount <= FINAL_WIDTH:
img = image[(int(center[1]) - amount):(int(center[1]) +
amount),
(int(center[0]) - amount):(int(center[0]) +
amount)]
return img
else:
return -1
else:
return -1
def get_hsv_mask(self, image, lower, upper):
return cv2.inRange(image, lower, upper)
def end_all(self):
self.fvs.release()
cv2.destroyAllWindows()
def draw_grid(self, im2, x_grid_num, y_grid_num):
#ret,frame = self.cap.read()
row = [0 for i in range(18)]
mat = np.zeros((12, 18), dtype=np.uint64)
#for i in range(12):
# mat.append([])
X = im2.shape[1]
Y = im2.shape[0]
start_x = 0
start_y = 0
end_x = X / 18
end_y = Y / 12
for i in range(18):
for j in range(12):
if i not in range(x_grid_num - 1,
x_grid_num + 2) or j not in range(
y_grid_num - 1, y_grid_num + 2):
im2 = cv2.rectangle(
im2, (start_x + (X / 18) * i, start_y + (Y / 12) * j),
(end_x + (X / 18) * i, end_y + (Y / 12) * j),
(0, 0, 255))
mat[j][i] = 0
else:
im2 = cv2.rectangle(
im2, (start_x + (X / 18) * i, start_y + (Y / 12) * j),
(end_x + (X / 18) * i, end_y + (Y / 12) * j),
(0, 0, 255), -1)
mat[j][i] = 1
#print "HI", mat[j][i]
'''
print "Printing mat..."
for i in range(12):
s = ""
for j in range(18):
s += str(mat[i][j]) + " "
print s
'''
MAT = np.copy(mat)
#print "MAT.shape", MAT.shape
return im2, MAT
'''
##increase image size and resoulation
new_img = img[int(bbox[1]):int(bbox[3]), int(bbox[0]):int(bbox[2])]
new_img = cv2.resize(new_img, (360, 360), interpolation = cv2.INTER_NEAREST)
cv2.imwrite(directory1 + f"image{b1}.jpg", new_img)
if count > 1:
break
#current_count += 1
total_count = len(set(counter))
#cv2.putText(img, "Current Vehicle Count: " + str(current_count), (0, 80), 0, 1, (0, 0, 255), 2)
cv2.putText(img, "Total Vehicle Count: " + str(total_count), (0,130), 0, 1, (0,0,255), 2)
fps = 1./(time.time()-t1)
cv2.putText(img, "FPS: {:.2f}".format(fps), (0,30), 0, 1, (0,0,255), 2)
#cv2.resizeWindow('output', 1024, 768)
cv2.imshow('output', img)
out.write(img)
if cv2.waitKey(1) == ord('q'):
break
vid.release()
out.release()
cv2.destroyAllWindows()
def _main_():
config_path = 'ncsmodel/config.json'
image_path = 'videos/uba.mp4'
keras.backend.tensorflow_backend.set_session(get_session())
with open(config_path) as config_buffer:
config = json.load(config_buffer)
###############################
# Make the model
###############################
input_size = (config['model']['input_size_h'],
config['model']['input_size_w'])
labels = config['model']['labels']
max_box_per_image = config['model']['max_box_per_image']
anchors = config['model']['anchors']
gray_mode = config['model']['gray_mode']
nb_class = 1
# Net Config
NN = Net(load_weights=True)
cv2_image = cv2.imread("images/person.jpg", 0)
image = NN.image
if config['model']['gray_mode']:
depth = 1
else:
depth = 3
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
if image_path[-4:] == '.mp4':
video_out = image_path[:-4] + '_detected' + image_path[-4:]
cap = FileVideoStream(image_path).start()
time.sleep(1.0)
fps = FPS().start()
fps_img = 0.0
counter = 0
tf_image = NN.image
while True:
start = time.time()
image = cap.read()
print(image.min(), image.max(), image.mean(), image.shape)
if depth == 1:
# convert video to gray
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# resize for plotting
resized_image = cv2.resize(gray_image,
input_size,
interpolation=cv2.INTER_CUBIC)
# convert to float
image_data = np.array(resized_image, dtype=np.float16)
image_data /= 255.
# dimensions for inference (1, w, h, c)
image_data = np.expand_dims(np.expand_dims(image_data, 0),
3) # 1, 256, 256, 1
# dimension for plot (w, h, c)
plot_image = np.expand_dims(resized_image, 2)
else:
if counter == 1:
print("Color image")
image_data = cv2.resize(image,
input_size,
interpolation=cv2.INTER_CUBIC)
#image = np.array(image, dtype='f')
#image = np.divide(image, 255.)
tm_inf = time.time()
netout = sess.run(NN.predict(),
feed_dict={tf_image: image_data})
netout = np.reshape(np.squeeze(netout, axis=0), (8, 8, 5, 6))
boxes = decode_netout(netout, anchors, nb_class)
fps_img = (fps_img + (1 / (time.time() - start))) / 2
#print( "Inference time: {:.4f}".format(time.time() - tm_inf) )
print(plot_image.shape)
image = draw_boxes(plot_image, boxes, labels)
#image = cv2.putText(image, "fps: {:.2f}".format(fps_img), (0, 20), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 0), 1, 4 )
cv2.imshow("Press q to quit", image)
fps.update()
#if counter == 10:
#print(image.sum(), boxes)
# time.sleep(1)
counter += 1
if cv2.getWindowProperty("Press q to quit",
cv2.WND_PROP_ASPECT_RATIO) < 0.0:
print("Window closed")
break
elif cv2.waitKey(1) & 0xFF == ord('q'):
print("Q pressed")
break
fps.stop()
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
cap.release()
else:
images = list(list_images(image_path))
for fname in images[100:]:
image = cv2.imread(fname)
tm_inf = time.time()
boxes = yolo.predict(image)
print("Inference time: {:.4f}".format(time.time() - tm_inf))
image = draw_boxes(image, boxes, config['model']['labels'])
cv2.imshow("Press q to quit", image)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
time.sleep(2)
cv2.destroyAllWindows()
class VideoCamera(object):
def __init__(self):
# Using OpenCV to capture from device 0. If you have trouble capturing
# from a webcam, comment the line below out and use a video file
# instead.
# self.video = cv2.VideoCapture(0)
# If you decide to use video.mp4, you must have this file in the folder
# as the main.py.
self.video = FileVideoStream("cropvideo.mp4").start()
def __del__(self):
self.video.release()
def detect_people(self, frame):
(rects, weights) = hog.detectMultiScale(frame, winStride=(8, 8), padding=(16, 16), scale=1.06)
rects = non_max_suppression(rects, probs=None, overlapThresh=0.65)
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 255), 2)
return frame
def detect_face(self, frame):
faces = face_cascade.detectMultiScale(frame, 1.1, 2, 0, (20, 20))
return faces
def draw_faces(self, frame, faces):
for (x, y, w, h) in faces:
xA = x
yA = y
xB = x + w
yB = y + h
cv2.rectangle(frame, (xA, yA), (xB, yB), (0, 255, 0), 2)
return frame
def background_subtraction(self, previous_frame, frame_resized_grayscale, min_area):
frameDelta = cv2.absdiff(previous_frame, frame_resized_grayscale)
thresh = cv2.threshold(frameDelta, 25, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.dilate(thresh, None, iterations=2)
cnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
temp = 0
for c in cnts:
if cv2.contourArea(c) > min_area:
temp = 1
return temp
def get_frame(self):
frame = self.video.read()
frame_resized_grayscale = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame_processed = self.detect_people(frame)
faces = self.detect_face(frame)
frame_processed = self.draw_faces(frame_processed, faces)
ret, jpeg = cv2.imencode('.jpg', frame_processed)
return jpeg.tobytes()
k = 0
if class_names[best_class_indices[k]] == "id1":
cv2.imwrite(
"/home/sai/kato/prediction/dataset/id1/User." +
str(id) + "." + str(sampleNum) + ".jpg", aligned)
elif class_names[best_class_indices[k]] == "id2":
cv2.imwrite(
"/home/sai/kato/prediction/dataset/id2/User." +
str(id) + "." + str(sampleNum) + ".jpg", aligned)
elif class_names[best_class_indices[k]] == "id3":
cv2.imwrite(
"/home/sai/kato/prediction/dataset/id3/User." +
str(id) + "." + str(sampleNum) + ".jpg", aligned)
elif class_names[best_class_indices[k]] == "id4":
cv2.imwrite(
"/home/sai/kato/prediction/dataset/id4/User." +
str(id) + "." + str(sampleNum) + ".jpg", aligned)
else:
print("unknown")
k = cv2.waitKey(1)
if k == ord('x'):
break
camera.release()
cv2.destroyAllWindows()