zoukankan      html  css  js  c++  java
  • opencv获取网络相机的图像-不用sdk

    海康相机

    优点:不用sdk直接网络获取

    缺点:速度有1-2秒的延迟

    使用型号

    1280*680分辨路

    #include <iostream>
    #include<opencv2/opencv.hpp>
    using namespace cv;
    using namespace std;
    int main()
    {
    	//1.从摄像头读入视频
    	//VideoCapture cap(0);
    
    	VideoCapture cap("rtsp://admin:fhy145145@192.168.1.62/Streaming/Channels/2"); //1 主码流 1 1280*680   2 次码流620*480
    	if (!cap.isOpened())
    	{
    		return 0;
    	}
    
    	Mat cam;
    	cap >> cam;//获取当前帧图像
    	cout << "Im.rows  = " << cam.rows << endl;
    	cout << "Im.cols  = " << cam.cols << endl;
    
    	//cout << "视频宽度=" << width << endl;
    	//cout << "视频高度=" << height << endl;
    
    	//2.循环显示每一帧
    	while (1)
    	{
    		
    		cap >> cam;//获取当前帧图像
    		if (!cam.empty())//如果某帧为空则退出循环
    		{
    	    namedWindow("相机", 0);
    		imshow("相机", cam);//显示当前帧图像
         
    	   waitKey(30);//延时30秒
    		}
    	}
    	return 0;
    }
    

      

    注: admin和12345分别是ip camera的用户名和密码,在浏览器上第一次登录摄像头的时候会进行设置;
    192.168.1.64是摄像头的默认IP,在浏览器中输入即可进入登录页面(如下);
    947235-20170717141904956-1178222844.png
    Channels/1和Channels/2分别对应主码流和子码流地址,两者的分辨率不同。IP摄像头无法通过opencv调节分辨率,只能在海康的监控界面的配置进行设置(如下)。
    947235-20170717142202097-697874552.png

    3. 摄像头校准(calibration)(optional)

    这个配置有很多,而且官方提供的校准文档很详细(戳这里),就不具体细讲了。需要python版本的代码的话可以直接fork这里;如果是c++版本的话可以参考这里

    python

    相机

    #!/usr/bin/env python3
    # -*- coding:utf-8 -*-
    import cv2
    import os
    font = cv2.FONT_HERSHEY_SIMPLEX
    #url='rtsp://admin:fhy145145@192.168.1.62/Streaming/Channels/1' #海康 
    url = 'http://192.168.1.89/webcapture.jpg?command=snap&channel=1' #雄迈
    #url='rtsp://192.168.1.89:554/user=admin&password=&channel=1&stream=0.sdp?'
    cam = cv2.VideoCapture(url)
    cam.set(3, 640) # set video width
    cam.set(4, 480) # set video height
    face_detector = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
    # For each person, enter one numeric face id
    face_id = input('
     请输入用户数字编号(只能是数字):   ')
    print("
     [INFO] Initializing face capture. Look the camera and wait ...")
    # Initialize individual sampling face countdsa
    count = 0
    while(True):
        ret, img = cam.read()
        cv2.putText(img, str(count), (5,80), font, 1, (255,255,255), 2)
       # cv2.putText(img, str("change face!"), (5,40), font, 1, (255,255,255), 2)
     
       # img = cv2.flip(img, -1) # flip video image vertically
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        faces = face_detector.detectMultiScale(gray, 1.3, 5)
        for (x,y,w,h) in faces:
            cv2.rectangle(img, (x,y), (x+w,y+h), (255,0,0), 2)   #
            cv2.putText(img, str("Perss s to save face!"), (5,40), font, 1, (255,255,255), 2)
           # cv2.imshow('image', img)
            k = cv2.waitKey(10) & 0xff # Press 'ESC' for exiting video
            if k == ord('s'):
                count += 1
                cv2.imwrite("dataset/User." + str(face_id) + '.' + str(count) + ".jpg", gray[y:y+h,x:x+w])
                break
            elif k == 27:
                break
        cv2.imshow('image', img)    
        k = cv2.waitKey(10) & 0xff # Press 'ESC' for exiting video
        if k == 27:
            break
        elif count >= 30: # Take 30 face sample and stop video
             break
        
    # Do a bit of cleanup
    print("
     [INFO] Exiting Program and cleanup stuff")
    cam.release()
    cv2.destroyAllWindows()
    

      

  • 相关阅读:
    Wireshark抓取网站用户名密码
    为ctf而生的web扫描器ctf-wscan
    windows下pip安装python模块时报错总结
    火绒剑获取IP位置
    shodan 搜寻公共摄像头
    肥猪流码农的逆袭之路(1)
    如何备份centos系统
    centos下nginx搭建drupal 8
    openstack学习笔记9-selfservice网络配置
    术语解释-什么是Overlay Network和Underlay Network
  • 原文地址:https://www.cnblogs.com/kekeoutlook/p/11759740.html
Copyright © 2011-2022 走看看