I am trying to build a dataset of face images, I have searched and find a code that is working fine with my laptop's webcam but when I am trying to capture with IP Camera which is usually used for surveillance than code is not working.

import cv2
import numpy as np

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_alt2.xml')

cap = cv2.VideoCapture(0)

count = 0
while True:
    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:
        cv2.imwrite("frame%d.jpg" % count, frame)
        count = count   1
    if cv2.waitKey(2) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

Another thing I want to mention my laptop Camera resolution is 640.0 480.0 and IP Cameras have 2560.0 1440.0. Please help me to capture all frames when face is present.

CodePudding user response：

To capture images from specific camera you need to change arguments in cv2.VideoCapture(argument). For example:

• cv2.VideoCapture(0): it's used to select the default camera, generally laptop inbuilt camera.
• cv2.VideoCapture(n) where n>=1: it's used to select the other external camera connect to laptop through usb/other ports
• cv2.VideoCapture('protocol://IP:port/1'): it's used to take input from network cameras(like in your case)
• Here protocol means: HTTP/RTSP etc.
• IP means hosting address: Example: 192.168.18.37
• port where the IP address is accessed

In this case it should be:

cv2.VideoCapture('rtsp://admin:[email protected]/H264?ch=2&subtype=0/1')

CodePudding user response：

The issue has been resolved after adjusting the resolution, I have added the line of code for frame adjustment frame = cv2.resize(frame, (1360, 768)) than code has started working properly.

This code might be helpful for anyone.

import cv2
import numpy as np

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_alt2.xml')

cap = cv2.VideoCapture('rtsp://admin:[email protected]/H264?ch=2&subtype=0/1')

count = 0
while True:
    ret,frame = cap.read()
    frame = cv2.resize(frame, (1360, 768))
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        cv2.imwrite("frame%d.jpg" % count, frame)
        count = count   1
    if cv2.waitKey(2) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

CodePudding user response：

Changing the resolution before image capture is more optimal. There would be no need to resize every subsequent frame.

Before the while loop set the width and height as follows:

cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 768)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 1380)

Different flags used for video streaming