背景差分法

背景差分法是一種很常用而且廣泛感測的技術，主要用於背景不動的情況下提取前景。它主要的原理是在當前幀和背景做減法，然後使用threshold進行二值化得到前景掩碼。下面是背景減法的示意圖。

背景差分法主要包含以下兩個步驟：
1.背景的建立
2.背景的更新
兩個關鍵點，第一個就是如何選擇背景，第二個就是什麼時候更新背景，這樣可以適應背景變化的情況，更新背景的快慢也很重要，如果更新慢了，快速運動的物體如果沒有重疊就認為是兩個物體了，如果更新快了，慢速運動的物體會被認為是背景，這樣就造成漏檢。
這裡學習一下在opencv中如何使用背景差分法。

程式碼

使用了兩個方法來產生前景掩碼：
1. cv::bgsegm::BackgroundSubtractorMog
2. cv::BackgroundSubtractorMog2

//opencv
#include "opencv2/imgcodecs.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/videoio.hpp"
#include <opencv2/highgui.hpp>
#include <opencv2/video.hpp>
//C
#include <stdio.h>
//C++
#include <iostream>
 

#include <sstream>
using namespace cv;
using namespace std;
// Global variables
Mat frame; //current frame
Mat fgMaskMOG2; //fg mask fg mask generated by MOG2 method
Ptr<BackgroundSubtractor> pMOG2; //MOG2 Background subtractor
char keyboard; //input from keyboard
void help();
void processVideo(char
 
* videoFilename);
void processImages(char* firstFrameFilename);
void help()
{
    cout
    << "--------------------------------------------------------------------------" << endl
    << "This program shows how to use background subtraction methods provided by "  << endl
    << " OpenCV. You can process both videos (-vid) and images (-img)."             << endl
                                                                                    << endl
    << "Usage:"                                                                     << endl
    << "./bg_sub {-vid <video filename>|-img <image filename>}"                     << endl
    << "for example: ./bg_sub -vid video.avi"                                       << endl
    << "or: ./bg_sub -img /data/images/1.png"                                       << endl
    << "--------------------------------------------------------------------------" << endl
    << endl;
}
int main(int argc, char* argv[])
{
    //print help information
    help();
    //check for the input parameter correctness
    if(argc != 3) {
        cerr <<"Incorret input list" << endl;
        cerr <<"exiting..." << endl;
        return EXIT_FAILURE;
    }
    //create GUI windows
    namedWindow("Frame");
    namedWindow("FG Mask MOG 2");
    //create Background Subtractor objects
    pMOG2 = createBackgroundSubtractorMOG2(); //MOG2 approach
    if(strcmp(argv[1], "-vid") == 0) {
        //input data coming from a video
        processVideo(argv[2]);
    }
    else if(strcmp(argv[1], "-img") == 0) {
        //input data coming from a sequence of images
        processImages(argv[2]);
    }
    else {
        //error in reading input parameters
        cerr <<"Please, check the input parameters." << endl;
        cerr <<"Exiting..." << endl;
        return EXIT_FAILURE;
    }
    //destroy GUI windows
    destroyAllWindows();
    return EXIT_SUCCESS;
}
void processVideo(char* videoFilename) {
    //create the capture object
    VideoCapture capture(videoFilename);
    if(!capture.isOpened()){
        //error in opening the video input
        cerr << "Unable to open video file: " << videoFilename << endl;
        exit(EXIT_FAILURE);
    }
    //read input data. ESC or 'q' for quitting
    keyboard = 0;
    while( keyboard != 'q' && keyboard != 27 ){
        //read the current frame
        if(!capture.read(frame)) {
            cerr << "Unable to read next frame." << endl;
            cerr << "Exiting..." << endl;
            exit(EXIT_FAILURE);
        }
        //update the background model
        pMOG2->apply(frame, fgMaskMOG2);
        //get the frame number and write it on the current frame
        stringstream ss;
        rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
                  cv::Scalar(255,255,255), -1);
        ss << capture.get(CAP_PROP_POS_FRAMES);
        string frameNumberString = ss.str();
        putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
                FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
        //show the current frame and the fg masks
        imshow("Frame", frame);
        imshow("FG Mask MOG 2", fgMaskMOG2);
        //get the input from the keyboard
        keyboard = (char)waitKey( 30 );
    }
    //delete capture object
    capture.release();
}
void processImages(char* fistFrameFilename) {
    //read the first file of the sequence
    frame = imread(fistFrameFilename);
    if(frame.empty()){
        //error in opening the first image
        cerr << "Unable to open first image frame: " << fistFrameFilename << endl;
        exit(EXIT_FAILURE);
    }
    //current image filename
    string fn(fistFrameFilename);
    //read input data. ESC or 'q' for quitting
    keyboard = 0;
    while( keyboard != 'q' && keyboard != 27 ){
        //update the background model
        pMOG2->apply(frame, fgMaskMOG2);
        //get the frame number and write it on the current frame
        size_t index = fn.find_last_of("/");
        if(index == string::npos) {
            index = fn.find_last_of("\\");
        }
        size_t index2 = fn.find_last_of(".");
        string prefix = fn.substr(0,index+1);
        string suffix = fn.substr(index2);
        string frameNumberString = fn.substr(index+1, index2-index-1);
        istringstream iss(frameNumberString);
        int frameNumber = 0;
        iss >> frameNumber;
        rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
                  cv::Scalar(255,255,255), -1);
        putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
                FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
        //show the current frame and the fg masks
        imshow("Frame", frame);
        imshow("FG Mask MOG 2", fgMaskMOG2);
        //get the input from the keyboard
        keyboard = (char)waitKey( 30 );
        //search for the next image in the sequence
        ostringstream oss;
        oss << (frameNumber + 1);
        string nextFrameNumberString = oss.str();
        string nextFrameFilename = prefix + nextFrameNumberString + suffix;
        //read the next frame
        frame = imread(nextFrameFilename);
        if(frame.empty()){
            //error in opening the next image in the sequence
            cerr << "Unable to open image frame: " << nextFrameFilename << endl;
            exit(EXIT_FAILURE);
        }
        //update the path of the current frame
        fn.assign(nextFrameFilename);
    }
}

關鍵程式碼說明

1. 建立三個全域性變數，frame用於儲存當前影象，fgMaskMog用於儲存前景掩碼，fgMaskMog2是第二種方法產生的前景掩碼。

Mat frame; //current frame
Mat fgMaskMOG; //fg mask generated by MOG method
Mat fgMaskMOG2; //fg mask fg mask generated by MOG2 method

1. 使用兩個方法產生前景掩碼，cv::BackgroundSubtractor。在本例中，使用預設的引數，你也可以嘗試其它引數。

Ptr<BackgroundSubtractor> pMOG; //MOG Background subtractor
Ptr<BackgroundSubtractor> pMOG2; //MOG2 Background subtractor
...
//create Background Subtractor objects
pMOG = createBackgroundSubtractorMOG(); //MOG approach

1. 傳入視訊還是單張影象，使用-vid引數傳入視訊 使用-img引數傳入影象

if(strcmp(argv[1], "-vid") == 0) {
  //input data coming from a video
  processVideo(argv[2]);
}
else if(strcmp(argv[1], "-img") == 0) {
  //input data coming from a sequence of images
  processImages(argv[2]);
}

1. 建議使用視訊進行測試。如果要停止，輸入“q”或者esc。

while( (char)keyboard != 'q' && (char)keyboard != 27 ){
  //read the current frame
  if(!capture.read(frame)) {
    cerr << "Unable to read next frame." << endl;
    cerr << "Exiting..." << endl;
    exit(EXIT_FAILURE);
  }

1. 每一幀影象都用於計算前景掩碼和更新背景，可以通過傳入引數來修改更新速度。

//update the background model
pMOG->apply(frame, fgMaskMOG);
pMOG2->apply(frame, fgMaskMOG2);

1. 在在上角顯示當前幀號。

//get the frame number and write it on the current frame
stringstream ss;
rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
          cv::Scalar(255,255,255), -1);
ss << capture.get(CAP_PROP_POS_FRAMES);
string frameNumberString = ss.str();
putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
        FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));

1. 然後顯示輸入影象和結果

//show the current frame and the fg masks
imshow("Frame", frame);
imshow("FG Mask MOG", fgMaskMOG);
imshow("FG Mask MOG 2", fgMaskMOG2);

1. 如果選擇圖片進行處理，需要輸入幾張影象。使用cv::imread進行處理。

//read the first file of the sequence
frame = imread(fistFrameFilename);
if(!frame.data){
  //error in opening the first image
  cerr << "Unable to open first image frame: " << fistFrameFilename << endl;
  exit(EXIT_FAILURE);
}
...
//search for the next image in the sequence
ostringstream oss;
oss << (frameNumber + 1);
string nextFrameNumberString = oss.str();
string nextFrameFilename = prefix + nextFrameNumberString + suffix;
//read the next frame
frame = imread(nextFrameFilename);
if(!frame.data){
  //error in opening the next image in the sequence
  cerr << "Unable to open image frame: " << nextFrameFilename << endl;
  exit(EXIT_FAILURE);
}
//update the path of the current frame
fn.assign(nextFrameFilename);

結果顯示：

結果顯示如果人停下了，那麼就檢測不到了。

儲存

儲存使用cv::imread就可以了，程式碼實現很簡單

string imageToSave = "output_MOG_" + frameNumberString + ".png";
bool saved = imwrite(imageToSave, fgMaskMOG);
if(!saved) {
  cerr << "Unable to save " << imageToSave << endl;
}