OpenCV：处理每一帧

Question

我想使用 OpenCV 编写一个跨平台应用程序进行视频捕获。在所有示例中，我发现来自相机的帧是使用抓取功能进行处理并等待一段时间。我想处理序列中的每一帧。我想定义我自己的回调函数，每次当一个新帧准备好处理时都会执行该函数（就像在 Windows 的 directshow 中，当您定义并放入您自己的过滤器时）用于此类目的）。

所以问题是：我该怎么做？

Answer 1

根据下面的代码，所有回调都必须遵循此定义：

IplImage* custom_callback(IplImage* frame);

此签名意味着回调将在系统检索到的每个帧上执行。在我的示例中， make_it_gray() 分配一个新图像来保存灰度转换的结果并返回它。这意味着您必须稍后在代码中释放该框架。我在代码中添加了有关它的注释。

请注意，如果您的回调需要大量处理，系统可能会跳过相机中的几帧。考虑一下 Paul R 和 diverscuba23 提出的建议。

#include <stdio.h>
#include "cv.h"
#include "highgui.h"


typedef IplImage* (*callback_prototype)(IplImage*);


/* 
 * make_it_gray: our custom callback to convert a colored frame to its grayscale version.
 * Remember that you must deallocate the returned IplImage* yourself after calling this function.
 */
IplImage* make_it_gray(IplImage* frame)
{
    // Allocate space for a new image
    IplImage* gray_frame = 0;
    gray_frame = cvCreateImage(cvSize(frame->width, frame->height), frame->depth, 1);
    if (!gray_frame)
    {
      fprintf(stderr, "!!! cvCreateImage failed!\n" );
      return NULL;
    }

    cvCvtColor(frame, gray_frame, CV_RGB2GRAY);
    return gray_frame; 
}

/*
 * process_video: retrieves frames from camera and executes a callback to do individual frame processing.
 * Keep in mind that if your callback takes too much time to execute, you might loose a few frames from 
 * the camera.
 */
void process_video(callback_prototype custom_cb)
{           
    // Initialize camera
    CvCapture *capture = 0;
    capture = cvCaptureFromCAM(-1);
    if (!capture) 
    {
      fprintf(stderr, "!!! Cannot open initialize webcam!\n" );
      return;
    }

    // Create a window for the video 
    cvNamedWindow("result", CV_WINDOW_AUTOSIZE);

    IplImage* frame = 0;
    char key = 0;
    while (key != 27) // ESC
    {    
      frame = cvQueryFrame(capture);
      if(!frame) 
      {
          fprintf( stderr, "!!! cvQueryFrame failed!\n" );
          break;
      }

      // Execute callback on each frame
      IplImage* processed_frame = (*custom_cb)(frame);

      // Display processed frame
      cvShowImage("result", processed_frame);

      // Release resources
      cvReleaseImage(&processed_frame);

      // Exit when user press ESC
      key = cvWaitKey(10);
    }

    // Free memory
    cvDestroyWindow("result");
    cvReleaseCapture(&capture);
}

int main( int argc, char **argv )
{
    process_video(make_it_gray);

    return 0;
}

编辑：

我更改了上面的代码，以便它打印当前帧速率并执行手动灰度转换。它们是对代码的小调整，我这样做是为了教育目的，这样人们就知道如何在像素级别执行操作。

#include <stdio.h>
#include <time.h>

#include "cv.h"
#include "highgui.h"


typedef IplImage* (*callback_prototype)(IplImage*);


/* 
 * make_it_gray: our custom callback to convert a colored frame to its grayscale version.
 * Remember that you must deallocate the returned IplImage* yourself after calling this function.
 */
IplImage* make_it_gray(IplImage* frame)
{
    // New IplImage* to store the processed image
    IplImage* gray_frame = 0; 

    // Manual grayscale conversion: ugly, but shows how to access each channel of the pixels individually
    gray_frame = cvCreateImage(cvSize(frame->width, frame->height), frame->depth, frame->nChannels);
    if (!gray_frame)
    {
      fprintf(stderr, "!!! cvCreateImage failed!\n" );
      return NULL;
    }

    for (int i = 0; i < frame->width * frame->height * frame->nChannels; i += frame->nChannels)
    {
        gray_frame->imageData[i] = (frame->imageData[i] + frame->imageData[i+1] + frame->imageData[i+2])/3;   //B
        gray_frame->imageData[i+1] = (frame->imageData[i] + frame->imageData[i+1] + frame->imageData[i+2])/3; //G
        gray_frame->imageData[i+2] = (frame->imageData[i] + frame->imageData[i+1] + frame->imageData[i+2])/3; //R
    }

    return gray_frame; 
}

/*
 * process_video: retrieves frames from camera and executes a callback to do individual frame processing.
 * Keep in mind that if your callback takes too much time to execute, you might loose a few frames from 
 * the camera.
 */
void process_video(callback_prototype custom_cb)
{           
    // Initialize camera
    CvCapture *capture = 0;
    capture = cvCaptureFromCAM(-1);
    if (!capture) 
    {
      fprintf(stderr, "!!! Cannot open initialize webcam!\n" );
      return;
    }

    // Create a window for the video 
    cvNamedWindow("result", CV_WINDOW_AUTOSIZE);    

    double elapsed = 0;
    int last_time = 0;
    int num_frames = 0;

    IplImage* frame = 0;
    char key = 0;
    while (key != 27) // ESC
    {    
      frame = cvQueryFrame(capture);
      if(!frame) 
      {
          fprintf( stderr, "!!! cvQueryFrame failed!\n" );
          break;
      }

      // Calculating framerate
      num_frames++;
      elapsed = clock() - last_time;
      int fps = 0;
      if (elapsed > 1)
      {
          fps = floor(num_frames / (float)(1 + (float)elapsed / (float)CLOCKS_PER_SEC));
          num_frames = 0;
          last_time = clock() + 1 * CLOCKS_PER_SEC;
          printf("FPS: %d\n", fps);
      }

      // Execute callback on each frame
      IplImage* processed_frame = (*custom_cb)(frame);  

      // Display processed frame
      cvShowImage("result", processed_frame);

      // Release resources
      cvReleaseImage(&processed_frame);

      // Exit when user press ESC
      key = cvWaitKey(10);
    }

    // Free memory
    cvDestroyWindow("result");
    cvReleaseCapture(&capture);
}

int main( int argc, char **argv )
{
    process_video(make_it_gray);

    return 0;
}

Answer 2

快速的想法是有两个线程，第一个线程负责抓取帧并在它们可用时通知第二个线程（将它们放入处理队列中），第二个线程以事件循环类型的方式完成所有处理。

请参阅 boost::thread 和 boost::signals2 ，因为这两个一起应该为我上面描述的提供大部分框架（队列除外）。