# outputs={'C:/UwAmp/www/output_video/' + video_name + '.mp4': None})
# ff.run()
#STOP THE TIMER, RESET IT, WHATEVER
#time_stop = time.time()
#video_length = time_stop - time_start;
#print(video_length) #TODO adjust FPS so this length actually matches the video length
#Write the highlights to a text file
# with open('C:/UwAmp/www/output_highlights/' + video_name + '.json', 'w') as outfile:
# json.dump(highlights, outfile)
# show the frame
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
counter += 1
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# if we are in the middle of recording a clip, wrap it up
if kcw.recording:
kcw.finish()
print("all done")
# do a bit of cleanup
vs.stop()
cv2.destroyAllWindows()
#p = TempImage(ext= conf["filetype"])
timestamp = datetime.datetime.now()
p = "./{}.{}".format(timestamp.strftime("%Y%m%d-%H%M%S"),conf["filetype"])
logging.debug("Path of Temp file = {}".format(p))
kcw.start(p, cv2.VideoWriter_fourcc(*conf["codec"]),conf["fps"])
# motion was not detectec, increment the still counter, clear the motion counter
else:
consecFrames += 1
motionFrames = 0
#if we are recording and the motion has stopped for long enough
#or we've reached the buffer length, stop recording
if kcw.recording and consecFrames >= conf["buffer_size"]:
logging.debug("Reached max buffer, closing the file")
kcw.finish()
consecFrames = 0
pedFrames = 0
peds = 0
#if Dropbox is turned on, upload the file
if conf["use_dropbox"]:
path = "{base_path}/{ds}/ {timestamp}.{extension}".format(
base_path=conf["dropbox_base_path"],ds=filedate, timestamp=ts,
extension=conf["filetype"])
uploader.queue_file( p, path, ts)
# put this frame into the video buffer
cv2.putText(frame, "Humans:{}:{}:{}".format(peds, motionFrames, consecFrames), (10, 40),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
kcw.update(frame)
class GenericDetector:
def __init__(self,
path,
headless,
buffer_size,
codec,
fps,
net,
confidence,
frameCount=32,
notifier=None,
url=None,
debugmemory=False,
blocking=False):
# initialize the video stream, allow the camera sensor to warm up,
# and initialize the FPS counter
print("[INFO] starting video stream...")
self.vs = VideoStream(src=0).start()
# vs = VideoStream(usePiCamera=True).start()
time.sleep(2.0)
self.fps = FPS().start()
# initialize the key clip writer and the motionFrames
# and consecFrames to track frames without motion
self.buffer_size = buffer_size
self.kcw = KeyClipWriter(bufSize=buffer_size)
self.consecFrames = 0 # number of frames with no motion
self.prev_detections = None
# initialize the output frame and a lock used to ensure thread-safe
# exchanges of the output frames (useful when multiple browsers/tabs
# are viewing the stream)
self.outputFrame = None
self.lock = threading.Lock()
self.path = path
self.headless = headless
self.codec = codec
self.fps_rate = fps
self.net = net
self.confidence = confidence
self.frameCount = frameCount
self.notifier = notifier
self.url = url
self.debugmemory = debugmemory
self.blocking = blocking
if not self.blocking:
self.inputQueue = Queue(maxsize=1)
self.outputQueue = Queue(maxsize=1)
def __del__(self):
self.kcw.finish()
# stop the timer and display FPS information
self.vs.stop()
self.fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
def loop_over_detections(self, frame, detections, w, h):
detected = False
msg = []
# 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 ensuring the `confidence` is
# greater than the minimum confidence
if confidence > self.confidence:
# extract the index of the class label from the
# `detections`, then compute the (x, y)-coordinates of
# the bounding box for the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# draw the timestamp
timestamp = datetime.datetime.now()
cv2.putText(frame, timestamp.strftime("%Y.%m.%d %H:%M:%S"),
(5, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[0],
2)
# draw the prediction on the frame
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
cv2.rectangle(frame, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(frame, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# record this frame
if self.prev_detections is None:
return
if np.array_equal(self.prev_detections, detections[0, 0, :, 1]):
return
detected = True
# if we are not already recording, start recording
if not self.kcw.recording:
difference = set(detections[0, 0, :, 1]).symmetric_difference(
set(self.prev_detections))
for o in difference:
msg.append(CLASSES[int(o)])
timestamp = datetime.datetime.now()
ts = timestamp.strftime("%Y%m%d-%H%M%S")
p = "{}/{}.avi".format(self.path, ts)
print(timestamp, 'Start recording', p)
self.kcw.start(p, cv2.VideoWriter_fourcc(*self.codec),
self.fps_rate)
if len(msg) > 0:
msg = ', '.join(msg)
msg = '{}: {} appeared'.format(ts, msg)
if self.url:
msg = msg + ' {}/video_feed'.format(self.url)
print(msg)
if self.notifier:
self.notifier(msg)
return detected
def detect_object_in_frame(self, frame):
frame = imutils.resize(frame, width=400)
# update the key frame clip buffer
self.kcw.update(frame)
# grab the frame dimensions and convert it to a blob
(h, w) = frame.shape[:2]
# run detection in current process
detections = self.classify_frame(frame)
if detections is not None:
if self.loop_over_detections(frame, detections, w, h):
self.consecFrames = 0
self.prev_detections = detections[
0, 0, :, 1] # save objects, detected on current frame
return frame
def _classify_frame(self, frame):
frame = cv2.resize(frame, (300, 300))
blob = cv2.dnn.blobFromImage(frame, 0.007843, (300, 300), 127.5)
# set the blob as input to our deep learning object
# detector and obtain the detections
self.net.setInput(blob)
return self.net.forward()
def classify_frame(self, frame):
if self.blocking:
return self._classify_frame(frame)
# if the input queue *is* empty, give the current frame to
# classify
if self.inputQueue.empty():
self.inputQueue.put(frame)
# if the output queue *is not* empty, grab the detections
if not self.outputQueue.empty():
return self.outputQueue.get()
def loop_classify_frame(self):
assert not self.blocking # only for non-blocking case
# keep looping
while True:
# check to see if there is a frame in our input queue
if self.inputQueue.empty():
continue
# grab the frame from the input queue, resize it, and
# construct a blob from it
frame = self.inputQueue.get()
detections = self._classify_frame(frame)
# write the detections to the output queue
self.outputQueue.put(detections)
def generate(self):
"Yield image/jpeg for web serving"
# grab global references to the output frame and lock variables
# loop over frames from the output stream
while True:
# wait until the lock is acquired
with self.lock:
# check if the output frame is available, otherwise skip
# the iteration of the loop
if self.outputFrame is None:
continue
# encode the frame in JPEG format
(flag, encodedImage) = cv2.imencode(".jpg", self.outputFrame)
# ensure the frame was successfully encoded
if not flag:
continue
# yield the output frame in the byte format
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' +
bytearray(encodedImage) + b'\r\n')
def detect_motion(outputDirectory):
global vs, outputFrame, lock
frameCount = 32
md = SingleMotionDetector(accumWeight=0.1)
total = 0
recordedFrameCount = 0
kcw = KeyClipWriter(bufSize=beforeAndAfterFrames)
lastFileName = None
while True:
# read the next frame from the video stream, resize it,
# convert the frame to grayscale, and blur it
frame = vs.read()
frame = imutils.resize(frame, width=600)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7, 7), 0)
# grab the current timestamp and draw it on the frame
timestamp = datetime.datetime.now()
cv2.putText(frame, timestamp.strftime("%A %d %B %Y %I:%M:%S%p"),
(10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.35,
(0, 255, 0), 1)
# if the total number of frames has reached a sufficient
# number to construct a reasonable background model, then
# continue to process the frame
if total > frameCount:
kcw.update(frame)
motion = md.detect(gray)
# check to see if motion was found in the frame
if motion is not None:
# unpack the tuple and draw the box surrounding the
# "motion area" on the output frame
(thresh, (minX, minY, maxX, maxY)) = motion
cv2.rectangle(frame, (minX, minY), (maxX, maxY), (0, 0, 255),
2)
if kcw.recording is False:
recordedFrameCount = 0
timestamp = datetime.datetime.now()
lastFileName = "{}/{}.mp4".format(
outputDirectory, timestamp.strftime("%Y%m%d-%H%M%S"))
kcw.start(lastFileName, cv2.VideoWriter_fourcc(*"MP4V"),
fps)
logging.info("Started recording")
if kcw.recording is True:
recordedFrameCount += 1
if recordedFrameCount > beforeAndAfterFrames:
logging.info("Stopped recording")
kcw.finish()
if lastFileName is not None:
ah.sendEvent(lastFileName)
# update the background model and increment the total number
# of frames read thus far
md.update(gray)
total += 1
# acquire the lock, set the output frame, and release the
# lock
with lock:
outputFrame = frame.copy()