Distinct People Counting using OpenCV Python - python-3.x

Question

I have a code that detects Cars in video and counts them, but there's an issue. If the same Car comes in the next frames, they get counted again. I tried from different resources but did not found any valid answer.
My Code
import cv2
backsub = cv2.bgsegm.createBackgroundSubtractorMOG()
capture = cv2.VideoCapture("C:/Users/chr04/Desktop/People and car counting/Car Counting/car video/video2.mp4")
best_id=0
i = 0
car = 0
if capture:
while True:
ret, frame = capture.read()
if ret:
fgmask = backsub.apply(frame, None, 0.01)
contours, hierarchy = cv2.findContours(fgmask.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_NONE)
try: hierarchy = hierarchy[0]
except: hierarchy = []
for contour, hier in zip(contours, hierarchy):
(x,y,w,h) = cv2.boundingRect(contour)
if w > 20 and h > 20:
best_id+=1
cv2.rectangle(frame, (x,y), (x+w,y+h), (255, 0, 0), 2)
cv2.putText(frame, str(best_id), (x,y-5), cv2.FONT_HERSHEY_SIMPLEX,
0.5, (255, 0, 0), 2)
print(best_id)
cv2.imshow("Track", frame)
cv2.imshow("background sub", fgmask)
key = cv2.waitKey(10)
if key == ord('q'):
break

Answer 1

You need to reset the counter variable in the loop again and again(as you get the images frame by frame). That seems to be the issue here.
What I understand from your code is that the best_id is your counter variable. So just initialize this variable inside the loop (best_id=0 inside while loop after if ret statement) and your code shall work fine as for every frame that you receive from the feed you need to reset this counter so that it can again start counting from 0 as done below.
if ret:
#initializing best_id variable
best_id = 0
fgmask = backsub.apply(frame, None, 0.01)
contours, hierarchy = cv2.findContours(fgmask.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_NONE)