Im trying to use Tracker Boosting after an object is detected. getting -215 Assertation Failure for tracker.init(frame,(centerX, centerY, width, height)). Its working fine with KCF, CSRT, MedianFlow or MIL. But im getting error with Boosting [closed]

asked 2020-06-14 14:32:09 -0500

Atique gravatar image

updated 2020-06-15 13:03:07 -0500

Code:

from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import dlib
import cv2
from cv2 import TrackerCSRT_create, TrackerMedianFlow_create, TrackerBoosting_create, TrackerKCF_create

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True,
                help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
                help="path to Caffe pre-trained model")
ap.add_argument("-i", "--input", type=str,
                help="path to optional input video file")
ap.add_argument("-o", "--output", type=str,
                help="path to optional output video file")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
                help="minimum probability to filter weak detections")
ap.add_argument("-s", "--skip-frames", type=int, default=25,
                help="# of skip frames between detections")
args = vars(ap.parse_args())

CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
           "sofa", "train", "tvmonitor"]

print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

if not args.get("input", False):
    print("[INFO] starting video stream...")
    # vs = VideoStream(src=0).start()
    vs = VideoStream('rtsp://admin:QVOSNZ@192.168.8.1:554/H.264').start()
    time.sleep(2.0)
else:
    print("[INFO] opening video file...")
    vs = cv2.VideoCapture(args["input"])

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
trackers = []
# trackers = cv2.MultiTracker_create()
trackableObjects = {}
totalFrames = 0
totalDown = 0
totalUp = 0

# start the frames per second throughput estimator
fps = FPS().start()
counter = 0
while True:
    frame = vs.read()
    frame = frame[1] if args.get("input", False) else frame
    confidences = []

    if args["input"] is not None and frame is None:
        break

    frame = imutils.resize(frame, width=500)
    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

    if W is None or H is None:
        (H, W) = frame.shape[:2]
    line_position_up = ((0, H // 4 + 30), (W, H // 4 + 30))
    line_position_down = ((0, 3 * (H // 4)), (W, 3 * (H // 4)))
    cv2.line(frame, line_position_up[0], line_position_up[1], (0, 255, 255), 2)
    cv2.line(frame, line_position_down[0], line_position_down[1], (0, 0, 255), 2)

    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)

    status = "Waiting"
    rects = []

    if totalFrames % args["skip_frames"] == 0:
        # set the status and initialize our new set of object trackers
        status = "Detecting"
        trackers = []

        blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 0.007843, (300, 300), 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 > 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] not in ["person", "car"]:
                    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 ...
(more)
edit retag flag offensive reopen merge delete

Closed for the following reason the question is answered, right answer was accepted by sturkmen
close date 2020-10-27 03:00:31.713522

Comments

tracker.init(frame,(centerX, centerY, width, height))

that's already wrong. you need the top-left corner, not centerX and centerY

in the end, it's complaining, that your box is out of image bounds

berak gravatar imageberak ( 2020-06-15 01:14:41 -0500 )edit