Step 1： 

Step 2： 
导入有用的framework

opencv2.framework需要自己下载 
opencv2.framework如下导入方式 

其他 .framework如下方式导入 

导入framework后如下图所示 
 
Step 3： 
下图1的位置将.m文件改为.mm文件 

Step 4： 
添加protocol  
这个delegate可以用来出来获取的视频图像 
Step 5：创建一个CvVideoCamera的实例 
@property (nonatomic,strong) CvVideoCamera *videoCamera;

Step 6：将videoCamera对象与imageView连接： 
self.videoCamera = [[CvVideoCamera alloc] initWithParentView:self.imageView]; 
self.videoCamera.delegate = self; 
self.videoCamera.defaultAVCaptureDevicePosition = AVCaptureDevicePositionBack;//调用摄像头前置或者后置 
self.videoCamera.defaultAVCaptureSessionPreset = AVCaptureSessionPreset640x480;//设置图像分辨率 
self.videoCamera.rotateVideo=YES;// 解决图像显示旋转90°问题 
self.videoCamera.grayscaleMode = NO;//获取图像是灰度还是彩色图像 
self.videoCamera.defaultFPS = 30;//摄像头频率 
只要简单的设置，现在videoCamera已经就绪了，只需要以下命令： 
[self.videoCamera start]; 
[self.videoCamera stop]; 
进行控制

Step 7：对获取的实时图像进行处理 
利用protocol的method：

-(void)processImage:(cv::Mat &)image {

//添加自己的图像处理算法 
if (!image.empty()) { 
if(image.channels()==4) 
{ cv::Mat gray; 
cv::cvtColor(image, gray, CV_BGRA2GRAY); 
cv::GaussianBlur(gray, gray, cv::Size(5,5), 1.2, 1.2); 
cv::Mat edges; 
cv::Canny(gray, edges, 0, 60); 
image.setTo(cv::Scalar::all(255)); 
image.setTo(cv::Scalar(0,128,255,255), edges); 
self.imageView.image = MatToUIImage(image); 
}else if(image.channels()==3) 
{ 
cv::Mat gray; 
cv::cvtColor(image, gray, CV_RGB2GRAY); 
cv::GaussianBlur(gray, gray, cv::Size(5,5), 1.2, 1.2); 
cv::Mat edges; 
cv::Canny(gray, edges, 0, 60); 
image.setTo(cv::Scalar::all(255)); 
image.setTo(cv::Scalar(0,128,255,255), edges); 
self.imageView.image = MatToUIImage(image); 
} 
else if(image.channels()==1){ 
cv::Mat gray; 
cv::GaussianBlur(image, gray, cv::Size(5,5), 1.2, 1.2); 
cv::Mat edges; 
cv::Canny(gray, edges, 0, 60); 
image.setTo(cv::Scalar::all(255)); 
image.setTo(cv::Scalar(0,128,255,255), edges); 
self.imageView.image = MatToUIImage(image); 
} 
else{ 
} 
} 
} 

有时会出现如下错误 
ld: ‘/Users///*/opencv2.framework/opencv2(cap_ios_video_camera.o)’ does not contain bitcode. You must rebuild it with bitcode enabled (Xcode setting ENABLE_BITCODE), obtain an updated library from the vendor, or disable bitcode for this target. for architecture arm64

Build Phases 收索bit code 将Enable Bitcode 后面的Yes改为No。

Opencv+IOS源码

Opencv For IOS 配置视频