# Parse input arguments

desc = 'Capture and display live camera video on Jetson TX2/TX1'

parser = argparse.ArgumentParser(description=desc)

parser.add_argument('--rtsp', dest='use_rtsp',

help='use IP CAM (remember to also set --uri)',

action='store_true')

parser.add_argument('--uri', dest='rtsp_uri',

help='RTSP URI, e.g. rtsp://192.168.1.64:554',

default=None, type=str)

parser.add_argument('--latency', dest='rtsp_latency',

help='latency in ms for RTSP [200]',

default=200, type=int)

parser.add_argument('--usb', dest='use_usb',

help='use USB webcam (remember to also set --vid)',

action='store_true')

parser.add_argument('--vid', dest='video_dev',

help='device # of USB webcam (/dev/video?) [1]',

default=1, type=int)

parser.add_argument('--width', dest='image_width',

help='image width [1920]',

default=1920, type=int)

parser.add_argument('--height', dest='image_height',

help='image height [1080]',

default=1080, type=int)

parser.add_argument("-t", "--tracker", type=str, default="kcf",help="OpenCV object tracker type", dest='a_tracker')

parser.add_argument("-p", "--prototxt", required=True,help="path to Caffe 'deploy' prototxt file", dest='a_proto')

parser.add_argument("-m", "--model", required=True,help="path to Caffe pre-trained model", dest='a_model')

parser.add_argument("-c", "--confidence", type=float, default=0.2,help="minimum probability to filter weak detections")

args = parser.parse_args()

gst_str = ('rtspsrc location={} latency={} ! '

'rtph264depay ! h264parse ! omxh264dec ! '

'nvvidconv ! '

'video/x-raw, width=(int){}, height=(int){}, '

'format=(string)BGRx ! '

'videoconvert ! appsink').format(uri, latency, width, height)

# We want to set width and height here, otherwise we could just do:

# return cv2.VideoCapture(dev)

gst_str = ('v4l2src device=/dev/video{} ! '

'video/x-raw, width=(int){}, height=(int){} ! '

'videoconvert ! appsink').format(dev, width, height)

gst_elements = str(subprocess.check_output('gst-inspect-1.0'))

if 'nvcamerasrc' in gst_elements:

# On versions of L4T prior to 28.1, add 'flip-method=2' into gst_str

gst_str = ('nvcamerasrc ! '

'video/x-raw(memory:NVMM), '

'width=(int)2592, height=(int)1458, '

'format=(string)I420, framerate=(fraction)30/1 ! '

'nvvidconv ! '

'video/x-raw, width=(int){}, height=(int){}, '

'format=(string)BGRx ! '

'videoconvert ! appsink').format(width, height)

elif 'nvarguscamerasrc' in gst_elements:

gst_str = ('nvarguscamerasrc ! '

'video/x-raw(memory:NVMM), '

'width=(int)1920, height=(int)1080, '

'format=(string)NV12, framerate=(fraction)30/1 ! '

'nvvidconv flip-method=2 ! '

'video/x-raw, width=(int){}, height=(int){}, '

'format=(string)BGRx ! '

'videoconvert ! appsink').format(width, height)

else:

raise RuntimeError('onboard camera source not found!')

cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)

cv2.resizeWindow(WINDOW_NAME, width, height)

cv2.moveWindow(WINDOW_NAME, 0, 0)

# initialize a dictionary that maps strings to their corresponding

# OpenCV object tracker implementations

OPENCV_OBJECT_TRACKERS = {

"csrt": cv2.TrackerCSRT_create,

"kcf": cv2.TrackerKCF_create,

"boosting": cv2.TrackerBoosting_create,

"mil": cv2.TrackerMIL_create,

"tld": cv2.TrackerTLD_create,

"medianflow": cv2.TrackerMedianFlow_create,

"mosse": cv2.TrackerMOSSE_create

}

CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",

"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",

"dog", "horse", "motorbike", "person", "pottedplant", "sheep",

"sofa", "train", "tvmonitor"]

# initialize OpenCV's special multi-object tracker

trackers = cv2.MultiTracker_create()

show_help = True

full_scrn = False

help_text = '"Esc" to Quit, "H" for Help, "F" to Toggle Fullscreen'

font = cv2.FONT_HERSHEY_PLAIN

frameCount=0

while True:

frameCount=frameCount+1

if cv2.getWindowProperty(WINDOW_NAME, 0) < 0:

# Check to see if the user has closed the window

# If yes, terminate the program

break

_, img = cap.read() # grab the next image frame from camera

# if our list of queues is empty then we know we have yet to

# create our first object tracker

print (str(frameCount))

if frameCount%5 == 0:

# initialize OpenCV's special multi-object tracker

trackers = cv2.MultiTracker_create()

# grab the frame dimensions and convert the frame to a blob

(h, w) = img.shape[:2]

t1=time.time()

blob = cv2.dnn.blobFromImage(img, 0.007843, (w, h), 127.5)

print ('dnn time: ',str((time.time()-t1)*1000000))

# pass the blob through the network and obtain the detections

# and predictions

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 > 0.2: #args["confidence"]:

# extract the index of the class label from the

# detections list

idx = int(detections[0, 0, i, 1])

label = CLASSES[idx]

# 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")

bb = (startX, startY, endX, endY)

box = (startX, startY, endX-startX, endY - startY)

# create a new object tracker for the bounding box and add it

# to our multi-object trackerQ

tracker = OPENCV_OBJECT_TRACKERS[args.a_tracker]()

trackers.add(tracker, img, box)

# grab the corresponding class label for the detection

# and draw the bounding box

cv2.rectangle(img, (startX, startY), (endX, endY),

(0, 255, 0), 2)

cv2.putText(img, label, (startX, startY - 15),

cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 255, 0), 2)

# otherwise, we've already performed detection so let's track

# multiple objects

else:

# grab the updated bounding box coordinates (if any) for each

# object that is being tracked

t1=time.time()

(success, boxes) = trackers.update(img)

print ('track time: ',str((time.time()-t1)*1000000))

# loop over the bounding boxes and draw then on the frame

for box in boxes:

(x, y, w, h) = [int(v) for v in box]

cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)

cv2.imshow(WINDOW_NAME, img)

key = cv2.waitKey(10)

if key == 27: # ESC key: quit program

break

elif key == ord('H') or key == ord('h'): # toggle help message

show_help = not show_help

elif key == ord('F') or key == ord('f'): # toggle fullscreen

full_scrn = not full_scrn

if full_scrn:

cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,

cv2.WINDOW_FULLSCREEN)

else:

cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,

args = parse_args()

print('Called with args:')

print(args)

print('OpenCV version: {}'.format(cv2.__version__))

# initialize the list of class labels MobileNet SSD was trained to

# detect

# load our serialized model from disk

print("[INFO] loading model...")

print(args.a_proto)

net = cv2.dnn.readNetFromCaffe(args.a_proto, args.a_model)

# initialize a dictionary that maps strings to their corresponding

# OpenCV object tracker implementations

OPENCV_OBJECT_TRACKERS = {

"csrt": cv2.TrackerCSRT_create,

"kcf": cv2.TrackerKCF_create,

"boosting": cv2.TrackerBoosting_create,

"mil": cv2.TrackerMIL_create,

"tld": cv2.TrackerTLD_create,

"medianflow": cv2.TrackerMedianFlow_create,

"mosse": cv2.TrackerMOSSE_create

}

if args.use_rtsp:

cap = open_cam_rtsp(args.rtsp_uri,

args.image_width,

args.image_height,

args.rtsp_latency)

elif args.use_usb:

cap = open_cam_usb(args.video_dev,

args.image_width,

args.image_height)

else: # by default, use the Jetson onboard camera

cap = open_cam_onboard(args.image_width,

args.image_height)

if not cap.isOpened():

sys.exit('Failed to open camera!')

open_window(args.image_width, args.image_height)

read_cam(cap,net,args)

cap.release()