def handle(self, **options): # construct the argument parse and parse the arguments ap = argparse.ArgumentParser() ap.add_argument("-c", "--confidence", type=float, default=0.5, help="minimum probability to filter weak detections") ap.add_argument("-t", "--threshold", type=float, default=0.3, help="threshold when applyong non-maxima suppression") args = vars(ap.parse_args()) # load the COCO class labels our YOLO model was trained on labelsPath = "yolo/yolo-coco/coco.names" LABELS = open(labelsPath).read().strip().split("\n") # initialize a list of colors to represent each possible class label np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") # derive the paths to the YOLO weights and model configuration weightsPath = "yolo/yolo-coco/yolov3.weights" configPath = "yolo/yolo-coco/yolov3.cfg" # load our YOLO object detector trained on COCO dataset (80 classes) # and determine only the *output* layer names that we need from YOLO print("[INFO] loading YOLO from disk...") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) ln = net.getLayerNames() ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()] # initialize the video stream, pointer to output video file, and # frame dimensions # old: vs = cv2.VideoCapture(args["input"]) vs = VideoStream(src=0).start() vs.rotation = 180 # allow camera to warm up time.sleep(2.0) writer = None (W, H) = (None, None) # loop over frames from the video file stream while True: print("looping") # key listener for q to quit the program # if the 'q' key is pressed, stop the loop key = cv2.waitKey(1) & 0xFF if key == ord("q"): break # read the next frame from the stream frame = vs.read() frame = imutils.rotate(frame, angle=180) #frame = white_balance(frame) cv2.imshow("frame", frame) #cv2.waitKey(0); # if the frame dimensions are empty, grab them if W is None or H is None: (H, W) = frame.shape[:2] # construct a blob from the input frame and then perform a forward # pass of the YOLO object detector, giving us our bounding boxes # and associated probabilities blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB=True, crop=False) net.setInput(blob) start = time.time() layerOutputs = net.forward(ln) end = time.time() # initialize our lists of detected bounding boxes, confidences, # and class IDs, respectively boxes = [] confidences = [] classIDs = [] # loop over each of the layer outputs for output in layerOutputs: # loop over each of the detections for detection in output: # extract the class ID and confidence (i.e., probability) # of the current object detection scores = detection[5:] classID = np.argmax(scores) confidence = scores[classID] # filter out weak predictions by ensuring the detected # probability is greater than the minimum probability if confidence > args["confidence"]: # scale the bounding box coordinates back relative to # the size of the image, keeping in mind that YOLO # actually returns the center (x, y)-coordinates of # the bounding box followed by the boxes' width and # height box = detection[0:4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") # use the center (x, y)-coordinates to derive the top # and and left corner of the bounding box x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) # CUSTOM: prevent other objects besides cars from being # processed if LABELS[classID] != 'car': continue # update our list of bounding box coordinates, # confidences, and class IDs boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) # CshoUSTOM: crop each object TODO cropped = frame[y:y + int(height), x:x + int(width)] if cropped.shape[0] < 1 or cropped.shape[1] < 1: continue color = get_colors(cropped, 3, False) cv2.imshow("Frame", cropped) cv2.waitKey(0) # apply non-maxima suppression to suppress weak, overlapping # bounding boxes idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"], args["threshold"]) # ensure at least one detection exists if len(idxs) > 0: # loop over the indexes we are keeping for i in idxs.flatten(): # extract the bounding box coordinates (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) # draw a bounding box rectangle and label on the frame color = [int(c) for c in COLORS[classIDs[i]]] cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2) text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i]) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2) # release the file pointers print("[INFO] cleaning up...") vs.stop()