25局部与分割-平均背景法和codebook背景学习法
主要原理:
1:平均背景法:首先统计给定样本图像的平均值和平均差,这里的平均值和平均差都是针对单个像素而言,对应平均值和平均差分别有一副mask图像对应。最后给定一幅判定图像,遍历图像中的每一个像素点,依据平均值和平均差是否在给定的范围内,如果在范围内,则是前景,否则为背景。
2:codebook背景学习法(内存占用比较大):
<1>学习过程中无移动的前景:首先为样本图像的每个像素都创建一个codebook,
之后遍历样本每一帧图像中的每一个像素点,记录每一个像素值在对应的codebook中,这样重复出现的背景点,都会刷新到codebook中,最后给定一幅判定图像,遍历图像中的每一个像素点,判断该像素点在codebook中是否有相应的记录,如有则是背景点,如果没有就是前景点。
<2>学习过程中有移动的前景:
和无移动的前景相对比,多了一步删除陈旧的码字(码字是码本中的一个结构);在统计样本过程中,会更新每一个codebook(码本)的时间记录,因为背景像素点出现的频率远高于前景像素点,当清除陈旧的codebook时,移动的前景像素点会被清除掉,最后给定一幅判定图像,遍历图像中的每一个像素点,判断该像素点在codebook中是否有相应的记录,如有则是背景点,如果没有就是前景点。
相应的代码:
<1>主代码:主要是调用平均背景法,和codebook背景学习法的接口
//命令行参数:1 50 D:\\openvc_project\\learn_opencv_code\\LearningOpenCV_Code\\tree.avi
#include "cv.h"
#include "highgui.h"
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include "AvgBackground.h"
#include "cv_yuv_codebook.h"
//VARIABLES for CODEBOOK METHOD:
codeBook *cB; //This will be our linear model of the image, a vector
//of lengh = height*width
int maxMod[CHANNELS]; //Add these (possibly negative) number onto max
// level when code_element determining if new pixel is foreground
int minMod[CHANNELS]; //Subract these (possible negative) number from min
//level code_element when determining if pixel is foreground
unsigned cbBounds[CHANNELS]; //Code Book bounds for learning
bool ch[CHANNELS]; //This sets what channels should be adjusted for background bounds
int nChannels = CHANNELS;
int imageLen = 0;
uchar *pColor; //YUV pointer
void help() {
printf("\nLearn background and find foreground using simple average and average difference learning method:\n"
"\nUSAGE:\n ch9_background startFrameCollection# endFrameCollection# [movie filename, else from camera]\n"
"If from AVI, then optionally add HighAvg, LowAvg, HighCB_Y LowCB_Y HighCB_U LowCB_U HighCB_V LowCB_V\n\n"
"***Keep the focus on the video windows, NOT the consol***\n\n"
"INTERACTIVE PARAMETERS:\n"
"\tESC,q,Q - quit the program\n"
"\th - print this help\n"
"\tp - pause toggle\n"
"\ts - single step\n"
"\tr - run mode (single step off)\n"
"=== AVG PARAMS ===\n"
"\t- - bump high threshold UP by 0.25\n"
"\t= - bump high threshold DOWN by 0.25\n"
"\t[ - bump low threshold UP by 0.25\n"
"\t] - bump low threshold DOWN by 0.25\n"
"=== CODEBOOK PARAMS ===\n"
"\ty,u,v- only adjust channel 0(y) or 1(u) or 2(v) respectively\n"
"\ta - adjust all 3 channels at once\n"
"\tb - adjust both 2 and 3 at once\n"
"\ti,o - bump upper threshold up,down by 1\n"
"\tk,l - bump lower threshold up,down by 1\n"
);
}
//
//USAGE: ch9_background startFrameCollection# endFrameCollection# [movie filename, else from camera]
//If from AVI, then optionally add HighAvg, LowAvg, HighCB_Y LowCB_Y HighCB_U LowCB_U HighCB_V LowCB_V
//
int main(int argc, char** argv)
{
IplImage* rawImage = 0, *yuvImage = 0; //yuvImage is for codebook method
IplImage *ImaskAVG = 0,*ImaskAVGCC = 0;
IplImage *ImaskCodeBook = 0,*ImaskCodeBookCC = 0;
CvCapture* capture = 0;
int startcapture = 1;
int endcapture = 30;
int c,n;
maxMod[0] = 3; //Set color thresholds to default values
minMod[0] = 10;
maxMod[1] = 1;
minMod[1] = 1;
maxMod[2] = 1;
minMod[2] = 1;
float scalehigh = HIGH_SCALE_NUM;
float scalelow = LOW_SCALE_NUM;
//--------------------------------------【获取视频源】----------------------------------------
//------判断是从文件还是摄像头中获取视频文件
if(argc < 3) {
printf("ERROR: Too few parameters\n");
help();
}else{
if(argc == 3){
printf("Capture from Camera\n");
capture = cvCaptureFromCAM( 0 );
}
else {
printf("Capture from file %s\n",argv[3]);
// capture = cvCaptureFromFile( argv[3] );
capture = cvCreateFileCapture( argv[3] );
if(!capture) { printf("Couldn't open %s\n",argv[3]); return -1;}
}
//------------------------------------------------------------------------------------------
//---------------------------------【通过命令行设置参数】-----------------------------------
if(isdigit(argv[1][0])) { //Start from of background capture
startcapture = atoi(argv[1]);
printf("startcapture = %d\n",startcapture);
}
if(isdigit(argv[2][0])) { //End frame of background capture
endcapture = atoi(argv[2]);
printf("endcapture = %d\n");
}
if(argc > 4){ //See if parameters are set from command line
//FOR AVG MODEL
if(argc >= 5){
if(isdigit(argv[4][0])){
scalehigh = (float)atoi(argv[4]);
}
}
if(argc >= 6){
if(isdigit(argv[5][0])){
scalelow = (float)atoi(argv[5]);
}
}
//FOR CODEBOOK MODEL, CHANNEL 0
if(argc >= 7){
if(isdigit(argv[6][0])){
maxMod[0] = atoi(argv[6]);
}
}
if(argc >= 8){
if(isdigit(argv[7][0])){
minMod[0] = atoi(argv[7]);
}
}
//Channel 1
if(argc >= 9){
if(isdigit(argv[8][0])){
maxMod[1] = atoi(argv[8]);
}
}
if(argc >= 10){
if(isdigit(argv[9][0])){
minMod[1] = atoi(argv[9]);
}
}
//Channel 2
if(argc >= 11){
if(isdigit(argv[10][0])){
maxMod[2] = atoi(argv[10]);
}
}
if(argc >= 12){
if(isdigit(argv[11][0])){
minMod[2] = atoi(argv[11]);
}
}
}
}
//------------------------------------------------------------------------------------------
//MAIN PROCESSING LOOP:
bool pause = false;
bool singlestep = false;
if( capture )
{
cvNamedWindow( "Raw", 1 );
cvNamedWindow( "AVG_ConnectComp",1);
cvNamedWindow( "ForegroundCodeBook",1);
cvNamedWindow( "CodeBook_ConnectComp",1);
cvNamedWindow( "ForegroundAVG",1);//声明窗口
int i = -1;
for(;;)
{
if(!pause){
// if( !cvGrabFrame( capture ))
// break;
// rawImage = cvRetrieveFrame( capture );
rawImage = cvQueryFrame( capture );//获取图像
++i;//count it//获取的帧数
// printf("%d\n",i);
if(!rawImage) //判断是否为空
break;
//REMOVE THIS FOR GENERAL OPERATION, JUST A CONVIENIENCE WHEN RUNNING WITH THE SMALL tree.avi file
if(i == 56){//获取56帧图像后就不获取新的图像
pause = 1;
printf("\n\nVideo paused for your convienience at frame 50 to work with demo\n"
"You may adjust parameters, single step or continue running\n\n");
help();
}
}
if(singlestep){//判断为单一步骤也停止获取图像
pause = true;
}
//First time:
if(0 == i) {//第一帧图像的处理流程
printf("\n . . . wait for it . . .\n"); //Just in case you wonder why the image is white at first
//---------------------------------【AVG METHOD ALLOCATION】-------------------------------
AllocateImages(rawImage);//根据原图像申请平均背景法所需要的内存
scaleHigh(scalehigh);//设置平均背景法的高阈值
scaleLow(scalelow);//设置平均背景法的低阈值
ImaskAVG = cvCreateImage( cvGetSize(rawImage), IPL_DEPTH_8U, 1 );//平均图像的掩码图像
ImaskAVGCC = cvCreateImage( cvGetSize(rawImage), IPL_DEPTH_8U, 1 );//平均图像的掩码图像的副本
cvSet(ImaskAVG,cvScalar(255));//置位白色(初始化全为背景)
//------------------------------------------------------------------------------------------
//---------------------------------【CODEBOOK METHOD ALLOCATION】---------------------------
yuvImage = cvCloneImage(rawImage);
ImaskCodeBook = cvCreateImage( cvGetSize(rawImage), IPL_DEPTH_8U, 1 );
ImaskCodeBookCC = cvCreateImage( cvGetSize(rawImage), IPL_DEPTH_8U, 1 );
cvSet(ImaskCodeBook,cvScalar(255));
imageLen = rawImage->width*rawImage->height;//计算所需要的codebook,每一个像素点都有一个codebook,三个通道
cB = new codeBook [imageLen];//申请codebook
//------------------------------------------------------------------------------------------
//---------------------------------【初始化CODEBOOK】---------------------------------------
for(int f = 0; f<imageLen; f++)
{
cB[f].numEntries = 0;
}
//------------------------------------------------------------------------------------------
//---------------------------------【初始化各通道的边界学习因子】---------------------------
for(int nc=0; nc<nChannels;nc++)
{
cbBounds[nc] = 10; //Learning bounds factor学习边界因子
}
//------------------------------------------------------------------------------------------
ch[0] = true; //Allow threshold setting simultaneously for all channels
ch[1] = true;
ch[2] = true; //设置各通道的阈值
}
//If we've got an rawImage and are good to go:
if( rawImage )
{
cvCvtColor( rawImage, yuvImage, CV_BGR2YCrCb );//YUV For codebook method
//This is where we build our background model
//---------------------------------【统计从自定义的开始帧到结束帧】--------------------------
if( !pause && i >= startcapture && i < endcapture ){
//LEARNING THE AVERAGE AND AVG DIFF BACKGROUND
accumulateBackground(rawImage);//累加图像,计算出平均值:IavgF/count,平均差:IdiffF/count
//LEARNING THE CODEBOOK BACKGROUND
pColor = (uchar *)((yuvImage)->imageData);
for(int c=0; c<imageLen; c++)
{
cvupdateCodeBook(pColor, cB[c], cbBounds, nChannels);//更新码本:更新计数,更新阈值或者创建新的码本
pColor += 3;//YUV三个通道
}
}
//-------------------------------------------------------------------------------------------
//----------------------------【如果是统计结束帧则创建平均背景法模板】-----------------------
//When done, create the background model
if(i == endcapture){//如果为设置的最后一帧,则创建模板
createModelsfromStats();//创建平均背景法的模板,最后得到阈值模板IhiF和IlowF
}
//-------------------------------------------------------------------------------------------
//-------------------------------【平均背景法查找前景像素】----------------------------------
//Find the foreground if any
if(i >= endcapture) {
//FIND FOREGROUND BY AVG METHOD:
backgroundDiff(rawImage,ImaskAVG);//结果ImaskAVG为前景和背景的掩码图像
cvCopy(ImaskAVG,ImaskAVGCC);//拷贝一份掩码图像
cvconnectedComponents(ImaskAVGCC);//传进去mask图像,然后在mask图像上绘制轮廓
//-------------------------------------------------------------------------------------------
//-------------------------------【学习背景法查找前景像素】----------------------------------
//FIND FOREGROUND BY CODEBOOK METHOD
uchar maskPixelCodeBook;
pColor = (uchar *)((yuvImage)->imageData); //3 channel yuv image
uchar *pMask = (uchar *)((ImaskCodeBook)->imageData); //1 channel image
for(int c=0; c<imageLen; c++)
{
//遍历一遍码本,判断当前像素是否在码本的范围内,背景为0,前景为255
maskPixelCodeBook = cvbackgroundDiff(pColor, cB[c], nChannels, minMod, maxMod);
*pMask++ = maskPixelCodeBook;
pColor += 3;
}
//This part just to visualize bounding boxes and centers if desired
cvCopy(ImaskCodeBook,ImaskCodeBookCC);
cvconnectedComponents(ImaskCodeBookCC);//传进去mask图像,然后在mask图像上绘制轮廓
}
//-------------------------------------------------------------------------------------------
//Display
cvShowImage( "Raw", rawImage );//显示原图像
cvShowImage( "AVG_ConnectComp",ImaskAVGCC);//前景掩码图像的轮廓[平均背景法]
cvShowImage( "ForegroundAVG",ImaskAVG);//前景的掩码图像[平均背景法]
cvShowImage( "ForegroundCodeBook",ImaskCodeBook);//前景掩码图像的轮廓[CodeBook法]
cvShowImage( "CodeBook_ConnectComp",ImaskCodeBookCC);//前景的掩码图像[CodeBook法]
//USER INPUT:
c = cvWaitKey(10)&0xFF;
//End processing on ESC, q or Q
if(c == 27 || c == 'q' | c == 'Q')
break;
//Else check for user input
//-------------------------------【修改参数】------------------------------------------------
switch(c)
{
case 'h':
help();
break;
case 'p':
pause ^= 1;
break;
case 's':
singlestep = 1;
pause = false;
break;
case 'r':
pause = false;
singlestep = false;
break;
//AVG BACKROUND PARAMS
case '-':
if(i > endcapture){
scalehigh += 0.25;
printf("AVG scalehigh=%f\n",scalehigh);
scaleHigh(scalehigh);
}
break;
case '=':
if(i > endcapture){
scalehigh -= 0.25;
printf("AVG scalehigh=%f\n",scalehigh);
scaleHigh(scalehigh);
}
break;
case '[':
if(i > endcapture){
scalelow += 0.25;
printf("AVG scalelow=%f\n",scalelow);
scaleLow(scalelow);
}
break;
case ']':
if(i > endcapture){
scalelow -= 0.25;
printf("AVG scalelow=%f\n",scalelow);
scaleLow(scalelow);
}
break;
//CODEBOOK PARAMS
case 'y':
case '0':
ch[0] = 1;
ch[1] = 0;
ch[2] = 0;
printf("CodeBook YUV Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case 'u':
case '1':
ch[0] = 0;
ch[1] = 1;
ch[2] = 0;
printf("CodeBook YUV Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case 'v':
case '2':
ch[0] = 0;
ch[1] = 0;
ch[2] = 1;
printf("CodeBook YUV Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case 'a': //All
case '3':
ch[0] = 1;
ch[1] = 1;
ch[2] = 1;
printf("CodeBook YUV Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case 'b': //both u and v together
ch[0] = 0;
ch[1] = 1;
ch[2] = 1;
printf("CodeBook YUV Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case 'i': //modify max classification bounds (max bound goes higher)
for(n=0; n<nChannels; n++){
if(ch[n])
maxMod[n] += 1;
printf("%.4d,",maxMod[n]);
}
printf(" CodeBook High Side\n");
break;
case 'o': //modify max classification bounds (max bound goes lower)
for(n=0; n<nChannels; n++){
if(ch[n])
maxMod[n] -= 1;
printf("%.4d,",maxMod[n]);
}
printf(" CodeBook High Side\n");
break;
case 'k': //modify min classification bounds (min bound goes lower)
for(n=0; n<nChannels; n++){
if(ch[n])
minMod[n] += 1;
printf("%.4d,",minMod[n]);
}
printf(" CodeBook Low Side\n");
break;
case 'l': //modify min classification bounds (min bound goes higher)
for(n=0; n<nChannels; n++){
if(ch[n])
minMod[n] -= 1;
printf("%.4d,",minMod[n]);
}
printf(" CodeBook Low Side\n");
break;
}
}
}
//-------------------------------------------------------------------------------------------
//-------------------------------【释放资源】------------------------------------------------
cvReleaseCapture( &capture );
cvDestroyWindow( "Raw" );
cvDestroyWindow( "ForegroundAVG" );
cvDestroyWindow( "AVG_ConnectComp");
cvDestroyWindow( "ForegroundCodeBook");
cvDestroyWindow( "CodeBook_ConnectComp");
DeallocateImages();
if(yuvImage) cvReleaseImage(&yuvImage);
if(ImaskAVG) cvReleaseImage(&ImaskAVG);
if(ImaskAVGCC) cvReleaseImage(&ImaskAVGCC);
if(ImaskCodeBook) cvReleaseImage(&ImaskCodeBook);
if(ImaskCodeBookCC) cvReleaseImage(&ImaskCodeBookCC);
delete [] cB;
}
//-------------------------------------------------------------------------------------------
else{ printf("\n\nDarn, Something wrong with the parameters\n\n"); help();
}
return 0;
}
<2>平均背景法具体实现代码:
AvgBackground.h:
///////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// Accumulate average and ~std (really absolute difference) image and use this to detect background and foreground
//
// Typical way of using this is to:
// AllocateImages();
// //loop for N images to accumulate background differences
// accumulateBackground();
// //When done, turn this into our avg and std model with high and low bounds
// createModelsfromStats();
// //Then use the function to return background in a mask (255 == foreground, 0 == background)
// backgroundDiff(IplImage *I,IplImage *Imask, int num);
// //Then tune the high and low difference from average image background acceptance thresholds
// float scalehigh,scalelow; //Set these, defaults are 7 and 6. Note: scalelow is how many average differences below average
// scaleHigh(scalehigh);
// scaleLow(scalelow);
// //That is, change the scale high and low bounds for what should be background to make it work.
// //Then continue detecting foreground in the mask image
// backgroundDiff(IplImage *I,IplImage *Imask, int num);
//
//NOTES: num is camera number which varies from 0 ... NUM_CAMERAS - 1. Typically you only have one camera, but this routine allows
// you to index many.
//
#ifndef AVGSEG_
#define AVGSEG_
#include "cv.h" // define all of the opencv classes etc.
#include "highgui.h"
#include "cxcore.h"
//IMPORTANT DEFINES:
#define NUM_CAMERAS 1 //This function can handle an array of cameras
#define HIGH_SCALE_NUM 7.0 //How many average differences from average image on the high side == background
#define LOW_SCALE_NUM 6.0 //How many average differences from average image on the low side == background
void AllocateImages(IplImage *I);
void DeallocateImages();
void accumulateBackground(IplImage *I, int number=0);
void scaleHigh(float scale = HIGH_SCALE_NUM, int num = 0);
void scaleLow(float scale = LOW_SCALE_NUM, int num = 0);
void createModelsfromStats();
void backgroundDiff(IplImage *I,IplImage *Imask, int num = 0);
#endif
AvgBackground.cpp:
#include "AvgBackground.h"
//GLOBALS
IplImage *IavgF[NUM_CAMERAS],*IdiffF[NUM_CAMERAS], *IprevF[NUM_CAMERAS], *IhiF[NUM_CAMERAS], *IlowF[NUM_CAMERAS];
IplImage *Iscratch,*Iscratch2,*Igray1,*Igray2,*Igray3,*Imaskt;
IplImage *Ilow1[NUM_CAMERAS],*Ilow2[NUM_CAMERAS],*Ilow3[NUM_CAMERAS],*Ihi1[NUM_CAMERAS],*Ihi2[NUM_CAMERAS],*Ihi3[NUM_CAMERAS];
float Icount[NUM_CAMERAS];
void AllocateImages(IplImage *I) //I is just a sample for allocation purposes
{
for(int i = 0; i<NUM_CAMERAS; i++){
IavgF[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
IdiffF[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
IprevF[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
IhiF[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
IlowF[i] = cvCreateImage(cvGetSize(I), IPL_DEPTH_32F, 3 );
Ilow1[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Ilow2[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Ilow3[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Ihi1[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Ihi2[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Ihi3[i] = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
cvZero(IavgF[i] );
cvZero(IdiffF[i] );
cvZero(IprevF[i] );
cvZero(IhiF[i] );
cvZero(IlowF[i] );
Icount[i] = 0.00001; //Protect against divide by zero
}
Iscratch = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
Iscratch2 = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 3 );
Igray1 = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Igray2 = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Igray3 = cvCreateImage( cvGetSize(I), IPL_DEPTH_32F, 1 );
Imaskt = cvCreateImage( cvGetSize(I), IPL_DEPTH_8U, 1 );
cvZero(Iscratch);
cvZero(Iscratch2 );
}
void DeallocateImages()
{
for(int i=0; i<NUM_CAMERAS; i++){
cvReleaseImage(&IavgF[i]);
cvReleaseImage(&IdiffF[i] );
cvReleaseImage(&IprevF[i] );
cvReleaseImage(&IhiF[i] );
cvReleaseImage(&IlowF[i] );
cvReleaseImage(&Ilow1[i] );
cvReleaseImage(&Ilow2[i] );
cvReleaseImage(&Ilow3[i] );
cvReleaseImage(&Ihi1[i] );
cvReleaseImage(&Ihi2[i] );
cvReleaseImage(&Ihi3[i] );
}
cvReleaseImage(&Iscratch);
cvReleaseImage(&Iscratch2);
cvReleaseImage(&Igray1 );
cvReleaseImage(&Igray2 );
cvReleaseImage(&Igray3 );
cvReleaseImage(&Imaskt);
}
// Accumulate the background statistics for one more frame
// We accumulate the images, the image differences and the count of images for the
// the routine createModelsfromStats() to work on after we're done accumulating N frames.
// I Background image, 3 channel, 8u
// number Camera number
void accumulateBackground(IplImage *I, int number)
{
static int first = 1;
cvCvtScale(I,Iscratch,1,0); //To float;//转化为浮点型矩阵
if (!first){
cvAcc(Iscratch,IavgF[number]);
cvAbsDiff(Iscratch,IprevF[number],Iscratch2);
cvAcc(Iscratch2,IdiffF[number]);
Icount[number] += 1.0;
}
first = 0;
cvCopy(Iscratch,IprevF[number]);
}
// Scale the average difference from the average image high acceptance threshold
void scaleHigh(float scale, int num)
{
cvConvertScale(IdiffF[num],Iscratch,scale); //Converts with rounding and saturation
cvAdd(Iscratch,IavgF[num],IhiF[num]);
cvCvtPixToPlane( IhiF[num], Ihi1[num],Ihi2[num],Ihi3[num], 0 );
}
// Scale the average difference from the average image low acceptance threshold
void scaleLow(float scale, int num)
{
cvConvertScale(IdiffF[num],Iscratch,scale); //Converts with rounding and saturation
cvSub(IavgF[num],Iscratch,IlowF[num]);
cvCvtPixToPlane( IlowF[num], Ilow1[num],Ilow2[num],Ilow3[num], 0 );
}
//Once you've learned the background long enough, turn it into a background model
void createModelsfromStats()
{
for(int i=0; i<NUM_CAMERAS; i++)
{
cvConvertScale(IavgF[i],IavgF[i],(double)(1.0/Icount[i]));
cvConvertScale(IdiffF[i],IdiffF[i],(double)(1.0/Icount[i]));
cvAddS(IdiffF[i],cvScalar(1.0,1.0,1.0),IdiffF[i]); //Make sure diff is always something确保平均差不为零
scaleHigh(HIGH_SCALE_NUM,i);
scaleLow(LOW_SCALE_NUM,i);
}
}
// Create a binary: 0,255 mask where 255 means forground pixel
// I Input image, 3 channel, 8u
// Imask mask image to be created, 1 channel 8u
// num camera number.
//判断当前图像中的像素是否在背景图像中
void backgroundDiff(IplImage *I,IplImage *Imask, int num) //Mask should be grayscale
{
cvCvtScale(I,Iscratch,1,0); //To float;
//Channel 1
cvCvtPixToPlane( Iscratch, Igray1,Igray2,Igray3, 0 );
cvInRange(Igray1,Ilow1[num],Ihi1[num],Imask);
//判断是否在背景范围内,因为前景值小于背景值,
//Channel 2
cvInRange(Igray2,Ilow2[num],Ihi2[num],Imaskt);
cvOr(Imask,Imaskt,Imask);
//Channel 3
cvInRange(Igray3,Ilow3[num],Ihi3[num],Imaskt);
cvOr(Imask,Imaskt,Imask);
//Finally, invert the results
//因为前景值小于背景值,此时前景为255,背景景值为0
cvSubRS( Imask, cvScalar(255), Imask);//执行该操作后前景为0,背景景值为255
}
//////////////////////////////////////////////////////////////////////////
/*
//Utility comparision function
gbCmp(IplImage *I1, IplImage *I2, IplImage *Imask, int op)
{
int len = I1->width*I1->height;
int x;
float *fp1 = (float *)I1->imageData;
float *fp2 = (float *)I2->imageData;
char *cp = Imask->imageData;
if(op == CV_CMP_GT)
{
for(x=0;x<len;x++)
{
if(*fp1++ > *fp2++)
*cp++ = 255;
else
*cp++ = 0;
}
}
else
{
for(x=0;x<len;x++)
{
if(*fp1++ < *fp2++)
*cp++ = 255;
else
*cp++ = 0;
}
}
}
void backgroundDiff(IplImage *I,IplImage *Imask, int num) //Mask should be grayscale
{
cvCvtScale(I,Iscratch,1,0); //To float;
cvCvtPixToPlane( Iscratch, Igray1,Igray2,Igray3, 0 );
gbCmp(Igray1,Ihi1[num],Imask,CV_CMP_GT);
gbCmp(Igray2,Ihi2[num],Imaskt,CV_CMP_GT);
cvOr(Imask,Imaskt,Imask);
gbCmp(Igray3,Ihi3[num],Imaskt,CV_CMP_GT);
cvOr(Imask,Imaskt,Imask);
gbCmp(Igray1,Ilow1[num],Imaskt,CV_CMP_LT);
cvOr(Imask,Imaskt,Imask);
gbCmp(Igray2,Ilow2[num],Imaskt,CV_CMP_LT);
cvOr(Imask,Imaskt,Imask);
gbCmp(Igray3,Ilow3[num],Imaskt,CV_CMP_LT);
cvOr(Imask,Imaskt,Imask);
//Some morphology
// cvErode( Imask, Imask, NULL, 1);
// cvMorphologyEx(Imask, Imask, NULL, NULL, CV_MOP_CLOSE, 1);
}
*/
<3>codebook背景学习法具体实现:
cv_yuv_codebook.h:
////////YUV CODEBOOK ////////////////////////////////////////////////////
// Gary Bradski, a pre-vacation doodle July 14, 2005
// Note that this is a YUV pixel model, must have one for each YUV pixel that you care about
///////////////////////////////////////////////////////////////////////////////////////////
/* How to call externally
//CONVERT IMAGE TO YUV
cvCvtColor( image, yuvImage, CV_BGR2YCrCb );
//DECLARATIONS:
#include "yuv_codebook.h"
// #define CHANNELS 3 //Could also use just 1 ("Y", brightness), but this is set in this header file.
//VARIABLES:
codeBook *cB; //This will be our linear model of the image, a vector of lengh = height*width
int maxMod[CHANNELS]; //Add these (possibly negative) number onto max level when code_element determining if new pixel is foreground
int minMod[CHANNELS]; //Subract these (possible negative) number from min level code_element when determining if pixel is foreground
unsigned cbBounds[CHANNELS]; //Code Book bounds for learning
int nChannels = CHANNELS;
int imageLen;
bool ch[CHANNELS];
...
//ALLOCATE IT WHEN YOU KNOW THE IMAGE SIZE
imageLen = image->width*image->height;
cB = new codeBook [imageLen];
for(int f = 0; f<imageLen; f++)
{
cB[f].numEntries = 0;
}
for(n=0; n<nChannels;n++)
{
cbBounds[n] = 10; //Learning bounds factor
}
maxMod[0] = 3; //Set color thresholds to more likely values
minMod[0] = 10;
maxMod[1] = 1;
minMod[1] = 1;
maxMod[2] = 1;
minMod[2] = 1;
...
//LEARNING BACKGROUND
uchar *pColor; //YUV pointer
if(learn)
{
pColor = (uchar *)((yuv)->imageData);
for(c=0; c<imageLen; c++)
{
cvupdateCodeBook(pColor, cB[c], cbBounds, nChannels);
pColor += 3;
}
learnCnt += 1;
}
//ELIMINATE SPURIOUS CODEBOOK ENTRIES (FOR SPEED)
int cleanedCnt; //will hold number of codebook entries eliminated
cleanedCnt = 0;
for(c=0; c<imageLen; c++)
{
cleanedCnt += cvclearStaleEntries(cB[c]);
}
...
//BACKGROUND SEGMENTATION
uchar *pMask,*pColor;
//For connected components bounding box and center of mass if wanted, else can leave out by default
int num = 5; //Just chose 5 arbitrarily, could be 1, 20, anything
CvRect bbs[5];
CvPoint centers[5];
if(modelExists)
{
pColor = (uchar *)((yuv)->imageData); //3 channel yuv image
pMask = (uchar *)((mask)->imageData); //1 channel image
for(c=0; c<imageLen; c++)
{
maskQ = cvbackgroundDiff(pColor, cB[c], nChannels, minMod, maxMod);
*pMask++ = maskQ;
pColor += 3;
}
//This part just to visualize bounding boxes and centers if desired
cvCopy(mask,maskCC);
num = 5; //
cvconnectedComponents(maskCC,1,4.0, &num, bbs, centers);
for(int f=0; f<num; f++)
{
CvPoint pt1, pt2; //Draw the bounding box in white
pt1.x = bbs[f].x;
pt1.y = bbs[f].y;
pt2.x = bbs[f].x+bbs[f].width;
pt2.y = bbs[f].y+bbs[f].height;
cvRectangle(maskCC,pt1,pt2, CV_RGB(255,255,255),2);
pt1.x = centers[f].x - 3; //Draw the center of mass in black
pt1.y = centers[f].y - 3;
pt2.x = centers[f].x +3;
pt2.y = centers[f].y + 3;
cvRectangle(maskCC,pt1,pt2, CV_RGB(0,0,0),2);
}
mw.paint(maskCC,0,1,0);
}
...
//EXAMPEL OF HOW TO ADJUST BACKGROUDN THRESHOLDS
ch[0] = 0; //ch[0]=>y, ch[1]=>u, ch[2]=>v
ch[1] = 1;
ch[2] = 1;
. . .
case '0':
ch[0] = 1;
ch[1] = 0;
ch[2] = 0;
printf("Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case '1':
ch[0] = 0;
ch[1] = 1;
ch[2] = 0;
printf("Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case '2':
ch[0] = 0;
ch[1] = 0;
ch[2] = 1;
printf("Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case '3':
ch[0] = 1;
ch[1] = 1;
ch[2] = 1;
printf("Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
case '4':
ch[0] = 0;
ch[1] = 1;
ch[2] = 1;
printf("Channels active: ");
for(n=0; n<nChannels; n++)
printf("%d, ",ch[n]);
printf("\n");
break;
. . .
case 'u': //modify max classification bounds
for(n=0; n<nChannels; n++){
if(ch[n])
maxMod[n] += 1;
printf("%.4d,",maxMod[n]);
}
printf("\n");
break;
case 'i': //modify max classification bounds
for(n=0; n<nChannels; n++){
if(ch[n])
maxMod[n] -= 1;
printf("%.4d,",maxMod[n]);
}
printf("\n");
break;
case ',': //modify min classification bounds (min bound goes lower)
for(n=0; n<nChannels; n++){
if(ch[n])
minMod[n] += 1;
printf("%.4d,",minMod[n]);
}
printf("\n");
break;
case '.': //modify min classification bounds (min bound goes higher)
for(n=0; n<nChannels; n++){
if(ch[n])
minMod[n] -= 1;
printf("%.4d,",minMod[n]);
}
printf("\n");
break;
...
//CLEAN UP
delete [] cB;
*/
///////////////////////////////////////////////////////////////////////////////////////////////
// Accumulate average and ~std deviation
#ifndef CVYUV_CB
#define CVYUV_CB
#include <cv.h> // define all of the opencv classes etc.
#include <highgui.h>
#include <cxcore.h>
#define CHANNELS 3
typedef struct ce {
uchar learnHigh[CHANNELS]; //High side threshold for learning
uchar learnLow[CHANNELS]; //Low side threshold for learning
uchar max[CHANNELS]; //High side of box boundary
uchar min[CHANNELS]; //Low side of box boundary
int t_last_update; //This is book keeping to allow us to kill stale entries
int stale; //max negative run (biggest period of inactivity)
} code_element;
typedef struct code_book {
code_element **cb;
int numEntries;
int t; //count every access
} codeBook;
///////////////////////////////////////////////////////////////////////////////////
// int updateCodeBook(uchar *p, codeBook &c, unsigned cbBounds)
// Updates the codebook entry with a new data point
//
// p Pointer to a YUV pixel
// c Codebook for this pixel
// cbBounds Learning bounds for codebook (Rule of thumb: 10)
// numChannels Number of color channels we're learning
//
// NOTES:
// cvBounds must be of size cvBounds[numChannels]
//
// RETURN
// codebook index
int cvupdateCodeBook(uchar *p, codeBook &c, unsigned *cbBounds, int numChannels = 3);
///////////////////////////////////////////////////////////////////////////////////
// uchar cvbackgroundDiff(uchar *p, codeBook &c, int minMod, int maxMod)
// Given a pixel and a code book, determine if the pixel is covered by the codebook
//
// p pixel pointer (YUV interleaved)
// c codebook reference
// numChannels Number of channels we are testing
// maxMod Add this (possibly negative) number onto max level when code_element determining if new pixel is foreground
// minMod Subract this (possible negative) number from min level code_element when determining if pixel is foreground
//
// NOTES:
// minMod and maxMod must have length numChannels, e.g. 3 channels => minMod[3], maxMod[3].
//
// Return
// 0 => background, 255 => foreground
uchar cvbackgroundDiff(uchar *p, codeBook &c, int numChannels, int *minMod, int *maxMod);
//UTILITES////////////////////////////////////////////////////////////////////////////////////
/////////////////////////////////////////////////////////////////////////////////
//int clearStaleEntries(codeBook &c)
// After you've learned for some period of time, periodically call this to clear out stale codebook entries
//
//c Codebook to clean up
//
// Return
// number of entries cleared
int cvclearStaleEntries(codeBook &c);
/////////////////////////////////////////////////////////////////////////////////
//int countSegmentation(codeBook *c, IplImage *I)
//
//Count how many pixels are detected as foreground
// c Codebook
// I Image (yuv, 24 bits)
// numChannels Number of channels we are testing
// maxMod Add this (possibly negative) number onto max level when code_element determining if new pixel is foreground
// minMod Subract this (possible negative) number from min level code_element when determining if pixel is foreground
//
// NOTES:
// minMod and maxMod must have length numChannels, e.g. 3 channels => minMod[3], maxMod[3].
//
//Return
// Count of fg pixels
//
int cvcountSegmentation(codeBook *c, IplImage *I, int numChannels, int *minMod, int *maxMod);
///////////////////////////////////////////////////////////////////////////////////////////
//void cvconnectedComponents(IplImage *mask, int poly1_hull0, float perimScale, int *num, CvRect *bbs, CvPoint *centers)
// This cleans up the forground segmentation mask derived from calls to cvbackgroundDiff
//
// mask Is a grayscale (8 bit depth) "raw" mask image which will be cleaned up
//
// OPTIONAL PARAMETERS:
// poly1_hull0 If set, approximate connected component by (DEFAULT) polygon, or else convex hull (0)
// perimScale Len = image (width+height)/perimScale. If contour len < this, delete that contour (DEFAULT: 4)
// num Maximum number of rectangles and/or centers to return, on return, will contain number filled (DEFAULT: NULL)
// bbs Pointer to bounding box rectangle vector of length num. (DEFAULT SETTING: NULL)
// centers Pointer to contour centers vectore of length num (DEFULT: NULL)
//
void cvconnectedComponents(IplImage *mask, int poly1_hull0=1, float perimScale=4.0, int *num=NULL, CvRect *bbs=NULL, CvPoint *centers=NULL);
#endif
cv_yuv_codebook.cpp:
////////YUV CODEBOOK
// Gary Bradski, July 14, 2005
#include "cv_yuv_codebook.h"
//GLOBALS FOR ALL CAMERA MODELS
//For connected components:
int CVCONTOUR_APPROX_LEVEL = 2; // Approx.threshold - the bigger it is, the simpler is the boundary
int CVCLOSE_ITR = 1; // How many iterations of erosion and/or dialation there should be
//#define CVPERIMSCALE 4 // image (width+height)/PERIMSCALE. If contour lenght < this, delete that contour
//For learning background
//Just some convienience macros
#define CV_CVX_WHITE CV_RGB(0xff,0xff,0xff)
#define CV_CVX_BLACK CV_RGB(0x00,0x00,0x00)
///////////////////////////////////////////////////////////////////////////////////
// int updateCodeBook(uchar *p, codeBook &c, unsigned cbBounds)
// Updates the codebook entry with a new data point
//
// p Pointer to a YUV pixel
// c Codebook for this pixel
// cbBounds Learning bounds for codebook (Rule of thumb: 10)
// numChannels Number of color channels we're learning
//
// NOTES:
// cvBounds must be of size cvBounds[numChannels]
//
// RETURN
// codebook index
int cvupdateCodeBook(uchar *p, codeBook &c, unsigned *cbBounds, int numChannels)
{
if(c.numEntries == 0) c.t = 0;
c.t += 1; //Record learning event
//SET HIGH AND LOW BOUNDS
int n;
unsigned int high[3],low[3];
for(n=0; n<numChannels; n++)
{
high[n] = *(p+n)+*(cbBounds+n);
if(high[n] > 255) high[n] = 255;
low[n] = *(p+n)-*(cbBounds+n);
if(low[n] < 0) low[n] = 0;
}
int matchChannel;
//SEE IF THIS FITS AN EXISTING CODEWORD
int i;
for(i=0; i<c.numEntries; i++)
{
matchChannel = 0;
for(n=0; n<numChannels; n++)
{
if((c.cb[i]->learnLow[n] <= *(p+n)) && (*(p+n) <= c.cb[i]->learnHigh[n])) //Found an entry for this channel
{
matchChannel++;
}
}
if(matchChannel == numChannels) //If an entry was found over all channels
{
c.cb[i]->t_last_update = c.t;
//adjust this codeword for the first channel
for(n=0; n<numChannels; n++)
{
if(c.cb[i]->max[n] < *(p+n))
{
c.cb[i]->max[n] = *(p+n);
}
else if(c.cb[i]->min[n] > *(p+n))
{
c.cb[i]->min[n] = *(p+n);
}
}
break;
}
}
//OVERHEAD TO TRACK POTENTIAL STALE ENTRIES
for(int s=0; s<c.numEntries; s++)
{
//This garbage is to track which codebook entries are going stale
int negRun = c.t - c.cb[s]->t_last_update;
if(c.cb[s]->stale < negRun) c.cb[s]->stale = negRun;
}
//ENTER A NEW CODE WORD IF NEEDED
if(i == c.numEntries) //No existing code word found, make a new one
{
code_element **foo = new code_element* [c.numEntries+1];
for(int ii=0; ii<c.numEntries; ii++)
{
foo[ii] = c.cb[ii];
}
foo[c.numEntries] = new code_element;
if(c.numEntries) delete [] c.cb;//清除之前的内存
c.cb = foo;//指向新的数据
for(n=0; n<numChannels; n++)
{
c.cb[c.numEntries]->learnHigh[n] = high[n];
c.cb[c.numEntries]->learnLow[n] = low[n];
c.cb[c.numEntries]->max[n] = *(p+n);
c.cb[c.numEntries]->min[n] = *(p+n);
}
c.cb[c.numEntries]->t_last_update = c.t;
c.cb[c.numEntries]->stale = 0;
c.numEntries += 1;
}
//SLOWLY ADJUST LEARNING BOUNDS
for(n=0; n<numChannels; n++)
{
if(c.cb[i]->learnHigh[n] < high[n]) c.cb[i]->learnHigh[n] += 1;
if(c.cb[i]->learnLow[n] > low[n]) c.cb[i]->learnLow[n] -= 1;
}
return(i);
}
///////////////////////////////////////////////////////////////////////////////////
// uchar cvbackgroundDiff(uchar *p, codeBook &c, int minMod, int maxMod)
// Given a pixel and a code book, determine if the pixel is covered by the codebook
//
// p pixel pointer (YUV interleaved)
// c codebook reference
// numChannels Number of channels we are testing
// maxMod Add this (possibly negative) number onto max level when code_element determining if new pixel is foreground
// minMod Subract this (possible negative) number from min level code_element when determining if pixel is foreground
//
// NOTES:
// minMod and maxMod must have length numChannels, e.g. 3 channels => minMod[3], maxMod[3].
//
// Return
// 0 => background, 255 => foreground
uchar cvbackgroundDiff(uchar *p, codeBook &c, int numChannels, int *minMod, int *maxMod)
{
int matchChannel;
//SEE IF THIS FITS AN EXISTING CODEWORD
int i;
for(i=0; i<c.numEntries; i++)
{
matchChannel = 0;
for(int n=0; n<numChannels; n++)
{
if((c.cb[i]->min[n] - minMod[n] <= *(p+n)) && (*(p+n) <= c.cb[i]->max[n] + maxMod[n]))
{
matchChannel++; //Found an entry for this channel
}
else
{
break;
}
}
if(matchChannel == numChannels)
{
break; //Found an entry that matched all channels
}
}
if(i >= c.numEntries) return(255);
return(0);
}
//UTILITES/////////////////////////////////////////////////////////////////////////////////////
/////////////////////////////////////////////////////////////////////////////////
//int clearStaleEntries(codeBook &c)
// After you've learned for some period of time, periodically call this to clear out stale codebook entries
//
//c Codebook to clean up
//
// Return
// number of entries cleared
int cvclearStaleEntries(codeBook &c)
{
int staleThresh = c.t>>1;
int *keep = new int [c.numEntries];
int keepCnt = 0;
//SEE WHICH CODEBOOK ENTRIES ARE TOO STALE
for(int i=0; i<c.numEntries; i++)
{
if(c.cb[i]->stale > staleThresh)
keep[i] = 0; //Mark for destruction
else
{
keep[i] = 1; //Mark to keep
keepCnt += 1;
}
}
//KEEP ONLY THE GOOD
c.t = 0; //Full reset on stale tracking
code_element **foo = new code_element* [keepCnt];
int k=0;
for(int ii=0; ii<c.numEntries; ii++)
{
if(keep[ii])
{
foo[k] = c.cb[ii];
foo[k]->stale = 0; //We have to refresh these entries for next clearStale
foo[k]->t_last_update = 0;
k++;
}
}
//CLEAN UP
delete [] keep;
delete [] c.cb;
c.cb = foo;
int numCleared = c.numEntries - keepCnt;
c.numEntries = keepCnt;
return(numCleared);
}
/////////////////////////////////////////////////////////////////////////////////
//int countSegmentation(codeBook *c, IplImage *I)
//
//Count how many pixels are detected as foreground
// c Codebook
// I Image (yuv, 24 bits)
// numChannels Number of channels we are testing
// maxMod Add this (possibly negative) number onto max level when code_element determining if new pixel is foreground
// minMod Subract this (possible negative) number from min level code_element when determining if pixel is foreground
//
// NOTES:
// minMod and maxMod must have length numChannels, e.g. 3 channels => minMod[3], maxMod[3].
//
//Return
// Count of fg pixels
//
int cvcountSegmentation(codeBook *c, IplImage *I, int numChannels, int *minMod, int *maxMod)
{
int count = 0,i;
uchar *pColor;
int imageLen = I->width * I->height;
//GET BASELINE NUMBER OF FG PIXELS FOR Iraw
pColor = (uchar *)((I)->imageData);
for(i=0; i<imageLen; i++)
{
if(cvbackgroundDiff(pColor, c[i], numChannels, minMod, maxMod))
count++;
pColor += 3;
}
return(count);
}
///////////////////////////////////////////////////////////////////////////////////////////
//void cvconnectedComponents(IplImage *mask, int poly1_hull0, float perimScale, int *num, CvRect *bbs, CvPoint *centers)
// This cleans up the forground segmentation mask derived from calls to cvbackgroundDiff
//
// mask Is a grayscale (8 bit depth) "raw" mask image which will be cleaned up
//
// OPTIONAL PARAMETERS:
// poly1_hull0 If set, approximate connected component by (DEFAULT) polygon, or else convex hull (0)
// perimScale Len = image (width+height)/perimScale. If contour len < this, delete that contour (DEFAULT: 4)
// num Maximum number of rectangles and/or centers to return, on return, will contain number filled (DEFAULT: NULL)
// bbs Pointer to bounding box rectangle vector of length num. (DEFAULT SETTING: NULL)
// centers Pointer to contour centers vectore of length num (DEFULT: NULL)
//mask:前景和背景的掩码图像
//void cvconnectedComponents(IplImage *mask, int poly1_hull0=1, float perimScale=4.0, int *num=NULL, CvRect *bbs=NULL, CvPoint *centers=NULL);
//传进去mask图像,然后在mask图像上绘制轮廓
void cvconnectedComponents(IplImage *mask, int poly1_hull0, float perimScale, int *num, CvRect *bbs, CvPoint *centers)
{
static CvMemStorage* mem_storage = NULL;
static CvSeq* contours = NULL;
//CLEAN UP RAW MASK
cvMorphologyEx( mask, mask, NULL, NULL, CV_MOP_OPEN, CVCLOSE_ITR );//执行开操作
cvMorphologyEx( mask, mask, NULL, NULL, CV_MOP_CLOSE, CVCLOSE_ITR );//执行开操作
//FIND CONTOURS AROUND ONLY BIGGER REGIONS
if( mem_storage==NULL ) mem_storage = cvCreateMemStorage(0);
else cvClearMemStorage(mem_storage);
CvContourScanner scanner = cvStartFindContours(mask,mem_storage,sizeof(CvContour),CV_RETR_EXTERNAL,CV_CHAIN_APPROX_SIMPLE);
CvSeq* c;
int numCont = 0;
//-------------------------------【轮廓的相应操作】---------------------------------------
while( (c = cvFindNextContour( scanner )) != NULL )
{
double len = cvContourPerimeter( c );
double q = (mask->height + mask->width) /perimScale; //calculate perimeter len threshold
if( len < q ) //Get rid of blob if it's perimeter is too small
{
cvSubstituteContour( scanner, NULL );//删除周长比较小的轮廓
}
else //Smooth it's edges if it's large enough
{
CvSeq* c_new;
if(poly1_hull0) //Polygonal approximation of the segmentation
//cvApproxPoly:将freeman链码转换为用多边形拟合,
c_new = cvApproxPoly(c,sizeof(CvContour),mem_storage,CV_POLY_APPROX_DP, CVCONTOUR_APPROX_LEVEL,0);
else //Convex Hull of the segmentation
//如果不是链码格式,则直接使用轮廓去
c_new = cvConvexHull2(c,mem_storage,CV_CLOCKWISE,1); //计算轮廓的凸包(包围轮廓的多边形)
cvSubstituteContour( scanner, c_new );//替换scanner序列中相对应的轮廓
numCont++;
}
}
contours = cvEndFindContours( &scanner );//和cvStartFindC对应ontours;此时并不会释放scanner,而是返回第一个元素
//-------------------------------------------------------------------------------------------
// PAINT THE FOUND REGIONS BACK INTO THE IMAGE
cvZero( mask );
IplImage *maskTemp;
//CALC CENTER OF MASS AND OR BOUNDING RECTANGLES
if(num != NULL)
{
int N = *num, numFilled = 0, i=0;
CvMoments moments;
double M00, M01, M10;
maskTemp = cvCloneImage(mask);
for(i=0, c=contours; c != NULL; c = c->h_next,i++ )
{
if(i < N) //Only process up to *num of them
{
cvDrawContours(maskTemp,c,CV_CVX_WHITE, CV_CVX_WHITE,-1,CV_FILLED,8);
//Find the center of each contour
if(centers != NULL)
{
cvMoments(maskTemp,&moments,1);
M00 = cvGetSpatialMoment(&moments,0,0);
M10 = cvGetSpatialMoment(&moments,1,0);
M01 = cvGetSpatialMoment(&moments,0,1);
centers[i].x = (int)(M10/M00);
centers[i].y = (int)(M01/M00);
}
//Bounding rectangles around blobs
if(bbs != NULL)
{
bbs[i] = cvBoundingRect(c);
}
cvZero(maskTemp);
numFilled++;
}
//Draw filled contours into mask
cvDrawContours(mask,c,CV_CVX_WHITE,CV_CVX_WHITE,-1,CV_FILLED,8); //draw to central mask
} //end looping over contours
*num = numFilled;
cvReleaseImage( &maskTemp);
}
//ELSE JUST DRAW PROCESSED CONTOURS INTO THE MASK
else
{
for( c=contours; c != NULL; c = c->h_next )
{
cvDrawContours(mask,c,CV_CVX_WHITE, CV_CVX_BLACK,-1,CV_FILLED,8);
}
}
}
<4>更新codebook(码本)的方法,删除陈旧的码字(码字是码本中的一个结构):
ClearStaleCB_Entries.cpp:
///////////////////////////////////////////////////////////////////
//int cvClearStaleEntries(codeBook &c)
// During learning, after you've learned for some period of time,
// periodically call this to clear out stale codebook entries
//
// c Codebook to clean up
//
// Return
// number of entries cleared
//用于学习有移动前景目标的背景
int cvClearStaleEntries(codeBook &c){
int staleThresh = c.t>>1;
int *keep = new int [c.numEntries];
int keepCnt = 0;
//SEE WHICH CODEBOOK ENTRIES ARE TOO STALE
for(int i=0; i<c.numEntries; i++){
if(c.cb[i]->stale > staleThresh)
keep[i] = 0; //Mark for destruction
else
{
keep[i] = 1; //Mark to keep
keepCnt += 1;
}
}
//KEEP ONLY THE GOOD
c.t = 0; //Full reset on stale tracking
code_element **foo = new code_element* [keepCnt];
int k=0;
for(int ii=0; ii<c.numEntries; ii++){
if(keep[ii])
{
foo[k] = c.cb[ii];
//We have to refresh these entries for next clearStale
foo[k]->t_last_update = 0;
k++;
}
}
//CLEAN UP
delete [] keep;
delete [] c.cb;
c.cb = foo;
int numCleared = c.numEntries - keepCnt;
c.numEntries = keepCnt;
return(numCleared);
}
最终结果:
从图可以看到codebook背景学习法要比平均背景法的效果好点。