opencv 视频场景识别

　　读出某一个文件夹下“jpg”后缀的全部图片后，用的OpenCV自带的人脸检测检测图片中的人脸，调整图片的大小写成一个avi视频。

　　主要是要记录一下CvVideoWriter的用法和如何从文件夹中读取某一后缀的全部文件。

代码：

#include "stdafx.h"

#include <opencv2\opencv.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <iostream>
#include <string>

#include <stdio.h> 
#include <stdlib.h> 
#include <assert.h> 
#include <math.h> 
#include <float.h> 
#include <limits.h> 
#include <time.h> 
#include <ctype.h>
#include <io.h>  

using namespace cv;
using namespace std;

void detectAndDraw( Mat& img, CascadeClassifier& cascade,
                   CascadeClassifier& nestedCascade,
                   double scale, bool tryflip );

int main(int argc, char** argv)  
{  
    CascadeClassifier cascade, nestedCascade;
    bool stop = false;
    //训练好的文件名称，放置在可执行文件同目录下
    cascade.load("haarcascade_frontalface_alt.xml");
    nestedCascade.load("haarcascade_eye_tree_eyeglasses.xml");

    // 图片集  
    string fileFolderPath = "F:\\picture";  
    string fileExtension = "jpg";  
    string fileFolder = fileFolderPath + "\\*." + fileExtension;  

    int codec = 0;  
    double frameRate = 1;  
    CvSize frameSize;  

    struct _finddata_t fileInfo;    // 文件信息结构体

    // 1. 第一次查找  
    long findResult = _findfirst(fileFolder.c_str(), &fileInfo);            
    if (findResult == -1)  
    {  
        _findclose(findResult);   
        return -1;  
    }  

    //2.设置视频的宽度和高度为 读取到的图片的最大宽度和最大高度
    int width = 0 ;
    int height = 0 ;
    IplImage* img;  
    string file_path ;
    do   
    {
        string temp_name =  fileInfo.name;
        file_path = fileFolderPath + "\\" +  temp_name ;
        img = cvLoadImage(file_path.c_str());    // 读入图片 

        if(img->width > width)
        {
            width = img->width ;
        }

        if(img->height > height)
        {
            height = img->height ;
        }
    } while (!_findnext(findResult, &fileInfo));
    _findclose(findResult); 

    // 3.生成视频  
    frameSize.width  = width ;
    frameSize.height = height ;
    int zero_H = 0 ;
    int zero_W = 0 ;
    CvVideoWriter* writer = cvCreateVideoWriter("output.avi",CV_FOURCC('X','V','I','D'),frameRate,frameSize);
    cvNamedWindow("Pic2avi",0);
    cvNamedWindow("img");  

    struct _finddata_t fileInfo2;    // 文件信息结构体
    long findResult2 = _findfirst(fileFolder.c_str(), &fileInfo2);            
    if (findResult2 == -1)  
    {  
        _findclose(findResult2);   
        return -1;  
    }  

    do   
    {  
        string t_name =  fileInfo2.name;
        string t_file_path = fileFolderPath + "\\" +  t_name ;
        IplImage* frame = cvLoadImage(t_file_path.c_str(), 1);    // 读入图片
        cvShowImage("img", frame); 
        IplImage* temp_frame = cvCreateImage(frameSize, IPL_DEPTH_8U, 3) ;

        if(frame->width <= frameSize.width)
        {
            zero_W = (frameSize.width - frame->width) / 2 ;
        }

        if(frame->height <= frameSize.height)
        {
            zero_H = (frameSize.height - frame->height) / 2 ;
        }

        CvRect roi =cvRect(zero_W, zero_H, frame->width, frame->height);
        cvSetImageROI(temp_frame,roi) ;

        cvResize(frame, temp_frame);
        cvResetImageROI(temp_frame) ;

        detectAndDraw( cv::Mat(temp_frame) , cascade, nestedCascade,2,0 );

        cvWriteFrame(writer,temp_frame); 


        cvShowImage("Pic2avi", temp_frame);   
        cvWaitKey(100);
        frame = NULL ;
        temp_frame = NULL ;

    } while (!_findnext(findResult2, &fileInfo2));    


    _findclose(findResult2);   


    return 0;  
}  

void detectAndDraw( Mat& img, CascadeClassifier& cascade,
                   CascadeClassifier& nestedCascade,
                   double scale, bool tryflip )
{
    int i = 0;
    double t = 0;
    //建立用于存放人脸的向量容器
    vector<Rect> faces, faces2;
    //定义一些颜色，用来标示不同的人脸
    const static Scalar colors[] =  { CV_RGB(0,0,255),
        CV_RGB(0,128,255),
        CV_RGB(0,255,255),
        CV_RGB(0,255,0),
        CV_RGB(255,128,0),
        CV_RGB(255,255,0),
        CV_RGB(255,0,0),
        CV_RGB(255,0,255)} ;
    //建立缩小的图片，加快检测速度
    //nt cvRound (double value) 对一个double型的数进行四舍五入，并返回一个整型数！
    Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
    //转成灰度图像，Harr特征基于灰度图
    cvtColor( img, gray, CV_BGR2GRAY );
    //改变图像大小，使用双线性差值
    resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
    //变换后的图像进行直方图均值化处理
    equalizeHist( smallImg, smallImg );

    //程序开始和结束插入此函数获取时间，经过计算求得算法执行时间
    t = (double)cvGetTickCount();
    //检测人脸
    //detectMultiScale函数中smallImg表示的是要检测的输入图像为smallImg，faces表示检测到的人脸目标序列，1.1表示
    //每次图像尺寸减小的比例为1.1，2表示每一个目标至少要被检测到3次才算是真的目标(因为周围的像素和不同的窗口大
    //小都可以检测到人脸),CV_HAAR_SCALE_IMAGE表示不是缩放分类器来检测，而是缩放图像，Size(30, 30)为目标的
    //最小最大尺寸
    cascade.detectMultiScale( smallImg, faces,
        1.1, 2, 0
        //|CV_HAAR_FIND_BIGGEST_OBJECT
        //|CV_HAAR_DO_ROUGH_SEARCH
        |CV_HAAR_SCALE_IMAGE
        ,
        Size(30, 30));
    //如果使能，翻转图像继续检测
    if( tryflip )
    {
        flip(smallImg, smallImg, 1);
        cascade.detectMultiScale( smallImg, faces2,
            1.1, 2, 0
            //|CV_HAAR_FIND_BIGGEST_OBJECT
            //|CV_HAAR_DO_ROUGH_SEARCH
            |CV_HAAR_SCALE_IMAGE
            ,
            Size(30, 30) );
        for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); r++ )
        {
            faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
        }
    }
    t = (double)cvGetTickCount() - t;
    //   qDebug( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
    for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
    {
        Mat smallImgROI;
        vector<Rect> nestedObjects;
        Point center;
        Scalar color = colors[i%8];
        int radius;

        double aspect_ratio = (double)r->width/r->height;
        if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
        {
            //标示人脸时在缩小之前的图像上标示，所以这里根据缩放比例换算回去
            center.x = cvRound((r->x + r->width*0.5)*scale);
            center.y = cvRound((r->y + r->height*0.5)*scale);
            radius = cvRound((r->width + r->height)*0.25*scale);
            circle( img, center, radius, color, 3, 8, 0 );
        }
        else
            rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
            cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
            color, 3, 8, 0);
        if( nestedCascade.empty() )
            continue;
        smallImgROI = smallImg(*r);
        //同样方法检测人眼
        nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
            1.1, 2, 0
            //|CV_HAAR_FIND_BIGGEST_OBJECT
            //|CV_HAAR_DO_ROUGH_SEARCH
            |CV_HAAR_DO_CANNY_PRUNING
            //|CV_HAAR_SCALE_IMAGE
            ,
            Size(30, 30) );
        for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
        {
            center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale);
            center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale);
            radius = cvRound((nr->width + nr->height)*0.25*scale);
            circle( img, center, radius, color, 3, 8, 0 );
        }
    }
    cv::imshow( "result", img );
}

代码中，

CvVideoWriter* writer = cvCreateVideoWriter("output.avi",CV_FOURCC('X','V','I','D'),frameRate,frameSize);

这部分用来设置生成的avi视频的各个参数。
　　
注释中的1和2就是从文件夹中读取某一后缀的全部文件。