How to do the real-time count object and detection with opencv-python?

Question

I am trying to do the science fair, And one of the parts is that I need to do the object count, But it is kinda tricky, Here's the code:

from imutils.video import FPS
import argparse
import imutils
import time
import cv2
tracker = cv2.LBPHRecognizer_create()
vs = cv2.VideoCapture(0)
initBB = None
while vs.isOpened():
    ret,frame = vs.read()
    cv2.line(frame, (933 , 462), (1170 , 462), (0,0,255), 3)
    if initBB is not None:
        (success, box) = tracker.update(frame)
        if success:
            (x, y, w, h) = [int(v) for v in box]
            cv2.rectangle(frame, (x, y), (x + w, y + h),
                (0, 255, 0), 2)
            cX = int((x + x+w) / 2.0)
            cY = int((y + y+h) / 2.0)
            cv2.circle(frame, (cX, cY), 4, (255, 0, 0), -1)
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
    if key == ord("s"):
        initBB = cv2.selectROI("Frame", frame, fromCenter=False,
            showCrosshair=True)
        tracker.init(frame, initBB)
        fps = FPS().start()
    elif key == ord("q"):
        break
else:
    vs.release()
cv2.destroyAllWindows()

And it is basically not running, Here's the error code:

  File "g:/資優班/科展/程式碼/HOG-real-time-test.py", line 8, in <module>
    tracker = cv2.LBPHRecognizer_create()
AttributeError: module 'cv2.cv2' has no attribute 'LBPHRecognizer_create'

I've tried searching the fixing ways, But it all doesn't help me, I think Maybe it is the OpenCV-python version problem, But still now sure and also still don't know how to fix, I'm kinda in a rush, Pls help me, masters, Thank you!