Tracking multiobjects recognized by Haar

asked 2018-08-10 04:06:40 -0500

Dakhoo gravatar image

I have made a simple code to recognize cars in a highway. The prediction works Ok, however the challenge comes when I would like to track them using the Multitrack method in OpenCV.

The problem is, in each frame the cascade recognizes say, 3 cars. These 3 cars feed the multiobject track, so for every next frame there would be tracked. However the cascade keep recognizing cars that goes into the tracking. Of course a car is the same, so it doesn't need to be recognized again and again.

I am using the video from here - so you can download it and rename it to uk_road.avi.

Here is the image of the result - which you can see multiple boxes are drawn because the multi-object and the cascade are not synchronized. image description

I am using python 3.6.6 and opencv version 3.4.2

#! /usr/bin/python

import cv2
import numpy as np
import imutils


def diffUpDown(img):
    # compare top and bottom size of the image
    # 1. cut image in two
    # 2. flip the top side
    # 3. resize to same size
    # 4. compare difference  
    height, width, depth = img.shape
    half = int(height/2)
    top = img[0:half, 0:width]
    bottom = img[half:half+half, 0:width]
    top = cv2.flip(top,1)
    bottom = cv2.resize(bottom, (32, 64)) 
    top = cv2.resize(top, (32, 64))  
    return ( mse(top,bottom) )


def diffLeftRight(img):
    # compare left and right size of the image
    # 1. cut image in two
    # 2. flip the right side
    # 3. resize to same size
    # 4. compare difference  
    height, width, depth = img.shape
    half = int(width/2)
    left = img[0:height, 0:half]
    right = img[0:height, half:half + half-1]
    right = cv2.flip(right,1)
    left = cv2.resize(left, (32, 64)) 
    right = cv2.resize(right, (32, 64))  
    return ( mse(left,right) )


def mse(imageA, imageB):
    err = np.sum((imageA.astype("float") - imageB.astype("float")) ** 2)
    err /= float(imageA.shape[0] * imageA.shape[1])
    return err

def isNewRoi(rx,ry,rw,rh,rectangles):
    for r in rectangles:
        if abs(r[0] - rx) < 30 and abs(r[1] - ry) < 30:
           return False  
    return True

def detectRegionsOfInterest(frame, cascade):
    scaleDown = 2
    frameHeight, frameWidth, fdepth = frame.shape 

    # Resize
    frame = cv2.resize(frame, (int(frameWidth/scaleDown), int(frameHeight/scaleDown))) 
    frameHeight, frameWidth, fdepth = frame.shape 

    # haar detection.
    cars = cascade.detectMultiScale(frame, 2, 1)

    newRegions = []
    minY = int(frameHeight*0.1)

    # iterate regions of interest
    for (x,y,w,h) in cars:
            roi = [x,y,w,h]
            roiImage = frame[y:y+h, x:x+w]
            if y > minY:
                diffX = diffLeftRight(roiImage)
                diffY = round(diffUpDown(roiImage))

                if diffX > 200 and diffY > 1200 :
                    rx,ry,rw,rh = roi
                    newRegions.append( [rx*scaleDown,ry*scaleDown,rw*scaleDown,rh*scaleDown] )

    return newRegions


def detectCars(filename):
    trackers = cv2.MultiTracker_create()
    rectangles = []
    cascade = cv2.CascadeClassifier('cars.xml')
    vc = cv2.VideoCapture(filename)

    if vc.isOpened():
        rval , frame = vc.read()
    else:
        rval = False

    frameCount = 0
    while frameCount < 40 :
        rval, frame = vc.read()
        frame = imutils.resize(frame, width=600)

        frameHeight, frameWidth, fdepth = frame ...
(more)
edit retag flag offensive close merge delete