在第一步中,計(jì)算背景的初始模型,而在第二步中,更新模型以適應(yīng)場(chǎng)景中的可能變化。
在本教程中,您將學(xué)習(xí)如何:
在下面你可以找到源代碼。我們將讓用戶選擇處理視頻文件或一系列圖像。
使用兩種不同的方法來(lái)生成兩個(gè)前景蒙版:
結(jié)果以及輸入數(shù)據(jù)顯示在屏幕上。源文件可以在這里下載。
//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);
}
}
我們討論上面代碼的主要部分:
Mat frame; //current frame
Mat fgMaskMOG; //fg mask generated by MOG method
Mat fgMaskMOG2; //fg mask fg mask generated by MOG2 method
Ptr<BackgroundSubtractor> pMOG; //MOG Background subtractor
Ptr<BackgroundSubtractor> pMOG2; //MOG2 Background subtractor
...
//create Background Subtractor objects
pMOG = createBackgroundSubtractorMOG(); //MOG approach
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]);
}
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);
}
//update the background model
pMOG->apply(frame, fgMaskMOG);
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", fgMaskMOG);
imshow("FG Mask MOG 2", fgMaskMOG2);
//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);
請(qǐng)注意,此示例僅適用于文件名格式為<n> .png的圖像序列,其中n是幀號(hào)(例如,7.png)。
-vid Video_001.avi
程序的輸出將如下所示:
-img 111_png / input / 1.png
程序的輸出將如下所示:
為了定量評(píng)估所得結(jié)果,我們需要:
為了保存輸出圖像,我們可以使用cv :: imwrite。添加以下代碼可以保存前景蒙版。
string imageToSave = "output_MOG_" + frameNumberString + ".png";
bool saved = imwrite(imageToSave, fgMaskMOG);
if(!saved) {
cerr << "Unable to save " << imageToSave << endl;
}
一旦我們收集了結(jié)果圖像,我們可以將它們與地面真實(shí)數(shù)據(jù)進(jìn)行比較。存在幾個(gè)公開(kāi)可用的背景減法序列,其中包含地面真值數(shù)據(jù)。如果您決定使用背景模型挑戰(zhàn)(BMC),則可以將結(jié)果圖像用作BMC向?qū)У?/a>輸入。向?qū)Э梢詫?duì)結(jié)果的準(zhǔn)確性計(jì)算不同的度量。
更多建議: