Building a tracking vision system for moving objects

In this section, we build a simple tacking vision system. We already learned how to detect a face in an image. Now we try to detect faces on video.

The idea is simple. We change a still image as source to a frame image from a camera. After calling read() from the VideoCapture object, we pass the frame image into face_cascade.detectMultiScale(). Then, we show it a picture dialog. That's it.

For implementation, type these scripts:

import numpy as np
import cv2

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
while True:
    # Capture frame-by-frame
    ret, frame = cap.read()

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        img = cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 255), 2)

    cv2.imshow('face tracking', frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break...