图像处理之前景检测（四）之自组织背景检测（SOBS）（转载）

       一种基于自组织神经网络（self-Organizing through artificial neural networks）的背景减除算法（简称SOBS算法，全名：Self-Organizing Background Subtraction），用于智能视频监控系统中的目标检测，该算法不仅对光照具有较强的鲁棒性，而且具有较强的实用性。

      具体原理参考下文，其中含有算法作者论文链接，比较详细。

      Belial_2010              基于自组织背景减除的运动目标检测算法

    

      算法代码实现见：

      ZengDong_1991     ackground Modeling and Foreground Detection -- SOBS

    

   这里对于上述代码进行了些许的更改和简单的注释，环境为VS2015+opencv3.2 contrib版。如下：

     

     头文件：BackgroundSubtractorSOBS.h

// Author : zengdong_1991
// Date   : 2016-06-13
// HomePage : http://blog.csdn.net/zengdong_1991
// Email  : 782083852@qq.com#pragma once
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/features2d/features2d.hpp>
#include "math.h"//! defines the parameters
#define WEIGHTS_N   3  //weight vertor 大小 = N^2
#define FRAME_NUM_K 45
#define EPSILON1 1.0
#define EPSILON2 0.008#define PARAM_C1 1.0
#define PARAM_C2 0.05
#define MAX_W 4.0
#define ALPHA_1 (PARAM_C1 / MAX_W)
#define ALPHA_2 (PARAM_C2 / MAX_W)#define GAMA 0.7
#define BEATA 1.0
#define TAU_S 40
#define TAU_H 48static const double m_weightW[WEIGHTS_N*WEIGHTS_N] = { 1.0, 2.0, 1.0, 2.0, 4.0, 2.0, 1.0, 2.0, 1.0 };//高斯权重的选择 class BackgroundSubtractorSOBS {
public://! full constructorBackgroundSubtractorSOBS(int trainFrameNum = FRAME_NUM_K,double epsilon1 = EPSILON1,double epsilon2 = EPSILON2,double c1 = PARAM_C1,double c2 = PARAM_C2,double gama = GAMA,double beta = BEATA,double tauS = TAU_S,double tauH = TAU_H,double maxW = MAX_W);//! default destructorvirtual ~BackgroundSubtractorSOBS();//! virtual void initialize(const cv::Mat& oInitImg, const cv::Mat& oROI);//! virtual void operator()(cv::InputArray image, cv::OutputArray fgmask, double learningRateOverride = 0);public:int m_trainFrameNum;double m_epsilon1;double m_epsilon2;double m_c1;double m_c2;double m_maxW;double m_alpha1;double m_alpha2;double m_gama;double m_beta;double m_tauS;double m_tauH;cv::Mat m_backgroundModel;   //背景模型：  n*rows, n*colssize_t m_frameNum = 0;cv::Mat m_ImgHSV;cv::Mat m_oROI;//! input image sizecv::Size m_oImgSize;//! input image channel sizesize_t m_nImgChannels;size_t m_height;size_t m_width;size_t m_pixelNum;//! input image typeint m_nImgType;bool findTheMatchVector(const cv::Vec3b& piexlVal, const size_t x, const size_t y, size_t& offSet_x, size_t& offSet_y, double eta); //true 匹配，false没有匹配void updateBackground(const cv::Vec3b& piexlVal, const size_t x, const size_t y, size_t& offSet_x, size_t& offSet_y, double alphaT);double getDistance(const cv::Vec3b& curr, const cv::Vec3b& bg);};

       算法函数主体：BackgroundSubtractorSOBS.cpp

// Author : zengdong_1991
// Date   : 2016-06-13
// HomePage : http://blog.csdn.net/zengdong_1991
// Email  : 782083852@qq.com
#include "BackgroundSubtractorSOBS.h"
#include <iostream>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>BackgroundSubtractorSOBS::BackgroundSubtractorSOBS(int trainFrameNum,double epsilon1, double epsilon2, double c1,double c2,double gama,double beta,double tauS, double tauH,double maxW): m_trainFrameNum(trainFrameNum), m_epsilon1(epsilon1), m_epsilon2(epsilon2), m_c1(c1), m_c2(c2), m_maxW(maxW), m_gama(gama), m_beta(beta), m_tauS(tauS), m_tauH(tauH)
{m_alpha1 = m_c1 / m_maxW;m_alpha2 = m_c2 / m_maxW;std::cout << "#########################Current Parameters Begin###################" << std::endl;std::cout << "m_trainFrameNum = " << m_trainFrameNum << std::endl;std::cout << "m_epsilon1 = " << m_epsilon1 << std::endl;std::cout << "m_epsilon2 = " << m_epsilon2 << std::endl;std::cout << "m_c1 = " << m_c1 << std::endl;std::cout << "m_c2 = " << m_c2 << std::endl;std::cout << "m_maxW = " << m_maxW << std::endl;std::cout << "m_alpha1 = " << m_alpha1 << std::endl;std::cout << "m_alpha2 = " << m_alpha2 << std::endl;std::cout << "m_gama = " << m_gama << std::endl;std::cout << "m_beta = " << m_beta << std::endl;std::cout << "m_tauS = " << m_tauS << std::endl;std::cout << "m_tauH = " << m_tauH << std::endl;std::cout << "#########################Current Parameters End###################" << std::endl;}BackgroundSubtractorSOBS::~BackgroundSubtractorSOBS() {}void BackgroundSubtractorSOBS::initialize(const cv::Mat& oInitImg, const cv::Mat& oROI)//初始化
{// == initCV_Assert(!oInitImg.empty() && oInitImg.cols > 0 && oInitImg.rows > 0);CV_Assert(oInitImg.isContinuous());CV_Assert(oInitImg.type() == CV_8UC3);   //必须是彩色图像if (oInitImg.type() == CV_8UC3){std::vector<cv::Mat> voInitImgChannels;cv::split(oInitImg, voInitImgChannels);if (!cv::countNonZero((voInitImgChannels[0] != voInitImgChannels[1]) | (voInitImgChannels[2] != voInitImgChannels[1])))std::cout << std::endl << "\tBackgroundSubtractorSuBSENSE : Warning, grayscale images should always be passed in CV_8UC1 format for optimal performance." << std::endl;}m_oImgSize = oInitImg.size();m_nImgType = oInitImg.type();m_nImgChannels = oInitImg.channels();m_height = oInitImg.rows;m_width = oInitImg.cols;m_pixelNum = m_height * m_width;m_frameNum = 1;//将第一帧转换到 HSV 空间cv::Mat hsv;cv::cvtColor(oInitImg, hsv, CV_BGR2HSV);    //H范围是 【0-->180】//根据hsv初始化背景模型  大小为 (n*rows, n*cols)m_backgroundModel.create(cv::Size(WEIGHTS_N*m_width, WEIGHTS_N*m_height), CV_8UC3);for (size_t x = 0; x < m_height; x++){for (size_t y = 0; y < m_width; y++){cv::Vec3b  val = hsv.at<cv::Vec3b>(x, y);for (size_t i = WEIGHTS_N*x; i < WEIGHTS_N*(x + 1); i++){for (size_t j = WEIGHTS_N*y; j < WEIGHTS_N*(y + 1); j++){m_backgroundModel.at<cv::Vec3b>(i, j) = val;}}}}//cv::Mat debugMat = m_backgroundModel;}void BackgroundSubtractorSOBS::operator()(cv::InputArray _image, cv::OutputArray _fgmask, double learningRateOverride)//对于后续图像进行对比操作，区分前景背景并颜色标注
{// == processcv::Mat oInputImg = _image.getMat();CV_Assert(oInputImg.type() == m_nImgType && oInputImg.size() == m_oImgSize);CV_Assert(oInputImg.isContinuous());_fgmask.create(m_oImgSize, CV_8UC1);cv::Mat oCurrFGMask = _fgmask.getMat();   //外界 mask 矩阵oCurrFGMask = cv::Scalar_<uchar>(0);//转换到HSV空间： cv::cvtColor(oInputImg, m_ImgHSV, CV_BGR2HSV);//cv::Mat debugMat = m_ImgHSV;m_frameNum++;size_t offSet_x = 0, offSet_y = 0;  //匹配偏移量double alphaT = m_alpha1 - (m_frameNum*(m_alpha1 - m_alpha2) / m_trainFrameNum); //公式（3）（4）  a(T)for (size_t x = 0; x < m_height; x++){for (size_t y = 0; y < m_width; y++){cv::Vec3b  val = m_ImgHSV.at<cv::Vec3b>(x, y);//calibration phase  执行 step 2--> 6if (m_frameNum <= m_trainFrameNum){//查找匹配                  if (findTheMatchVector(val, x, y, offSet_x, offSet_y, m_epsilon1)){updateBackground(val, x, y, offSet_x, offSet_y, alphaT);oCurrFGMask.at<uchar>(x, y) = 0;}else{oCurrFGMask.at<uchar>(x, y) = 255;}}//on line phase  执行 step 2-->10             else{if (findTheMatchVector(val, x, y, offSet_x, offSet_y, m_epsilon2)){updateBackground(val, x, y, offSet_x, offSet_y, m_alpha2);oCurrFGMask.at<uchar>(x, y) = 0;}/*else if (isShadow(val, x, y, offSet_x, offSet_y)){oCurrFGMask.at<uchar>(x, y) = 0;}*/else{oCurrFGMask.at<uchar>(x, y) = 255;}}}}}
void BackgroundSubtractorSOBS::updateBackground(const cv::Vec3b& piexlVal, const size_t x, const size_t y, size_t& offSet_x, size_t& offSet_y, double alphaT)//背景更新
{//  cv::Vec3b* ptrVec = m_backgroundModel.ptr<cv::Vec3b>(0);int pad = (WEIGHTS_N - 1) / 2;//当前匹配像素的坐标是    (nx+offset_x, ny+offset_y), 更新其周围的 N*N像素，如下：for (int i = -pad; i <= pad; i++){int coordinateX = WEIGHTS_N*x + offSet_x + i;if (coordinateX < 0 || coordinateX >= WEIGHTS_N*m_height)   //边界保护continue;for (int j = -pad; j <= pad; j++){int coordinateY = WEIGHTS_N*y + offSet_y + j;if (coordinateY < 0 || coordinateY >= WEIGHTS_N*m_width)  //边界保护continue;cv::Vec3b& pixelValBg = m_backgroundModel.at<cv::Vec3b>(coordinateX, coordinateY);double alpha = alphaT * m_weightW[(i + pad)*WEIGHTS_N + j + pad];  //【未解决】 w 怎么归一化...现在是【1,2,1；...】/*防止损失精度还是不这么做好了*///【未解决】 测试以下是否相等...pixelValBg = (1 - alpha)*pixelValBg + alpha*piexlVal;//cv::Vec3b At_1 = (1 - alpha)*pixelValBg;//cv::Vec3b Pt = alpha * piexlVal;//pixelValBg = At_1 + Pt;//cv::Vec3b test = pixelValBg;int a = 0;}}}bool BackgroundSubtractorSOBS::findTheMatchVector(const cv::Vec3b& piexlVal, const size_t x, const size_t y, size_t& offSet_x, size_t& offSet_y, double eta)//判断对应点是否符合属于背景条件
{cv::Mat temp = m_backgroundModel;//9个像素值...for (size_t i = 0; i < WEIGHTS_N; i++){for (size_t j = 0; j < WEIGHTS_N; j++){cv::Vec3b piexlValBg = m_backgroundModel.at<cv::Vec3b>(WEIGHTS_N*x + i, WEIGHTS_N*y + j);//当前像素与背景像素距离小于阈值double dist = getDistance(piexlVal, piexlValBg);if (dist < eta){offSet_x = i;offSet_y = j;return true;}}}return false;
}
double BackgroundSubtractorSOBS::getDistance(const cv::Vec3b& curr, const cv::Vec3b& bg)//求取HSV Color Hexcone距离
{//opencv BGR2HSV中的H分量范围属于【0-->180】，将其隐射回【0-->360°(2*pi)】double hRatio = 2 * CV_PI / 180.0;double sRatio = 1. / 255.;double vRatio = 1. / 255.;double h1 = (double)curr[0] * hRatio;double s1 = (double)curr[1] * sRatio;double v1 = (double)curr[2] * vRatio;double h2 = (double)bg[0] * hRatio;double s2 = (double)bg[1] * sRatio;double v2 = (double)bg[2] * vRatio;double distance = (v1*s1*cos(h1) - v2*s2*cos(h2))*(v1*s1*cos(h1) - v2*s2*cos(h2)) +(v1*s1*sin(h1) - v2*s2*sin(h2))*(v1*s1*sin(h1) - v2*s2*sin(h2)) +(v1 - v2)*(v1 - v2);return (distance);}

       主函数：main.cpp

// Author : zengdong_1991
// Date   : 2016-06-13
// HomePage : http://blog.csdn.net/zengdong_1991
// Email  : 782083852@qq.com
#include <iostream>
#include<opencv.hpp>#include "BackgroundSubtractorSOBS.h"using namespace std;
using namespace cv;int main(int argc, char **argv)
{VideoCapture cap("E:\\素材\\2.mp4");Mat frame;cap >> frame;BackgroundSubtractorSOBS bgs;int key = 0;bool initialized = false;cv::Mat img_mask;cv::Mat img_bkgmodel;while (key != 'q'){cap>>frame ;if (frame.empty() == 1) {std::cerr << "Cannot open video!" << std::endl;return 1;}cv::Mat img_input(frame);if (!initialized){bgs.initialize(img_input, cv::Mat());initialized = true;continue;}bgs(img_input, img_mask);//cv::medianBlur(img_mask, img_mask, 5);if (!img_mask.empty()){//cv::medianBlur(img_mask, img_mask, 5);cv::imshow("output", img_mask);}cv::imshow("input", img_input);cv::waitKey(1);//    key = cvWaitKey(1);}//cvDestroyAllWindows();//cvReleaseCapture(&capture);return 0;
}

运行结果：(现在看，速度确实有些慢）。