TLD(Tracking-Learning-Detection)算法学习与源码解析（2）之runtld.cpp源码解析
TLD(Tracking-Learning-Detection)算法学习与源码解析（二）之runtld.cpp源码解析
本序列文章的目的是总结一下这段时间所学到的，主要分为以下几部分，本章是第二部分。
1 算法概述
2 runtld.cpp源码解析
3 tld.cpp源码解析
4 LKTracker(重点)
5 FerNNClassifier.cpp源码解析（重点）
6 tld_utils.cpp源码解析
runtld.cpp这个是main函数所在的文件，其实没什么好看的，就是一个框。知道下面这些就可以了:
程序从parameters.yml文件读取一些初始化参数（一些阈值什么的），
绑定鼠标事件（用户需要用鼠标画一个矩形来标志目标窗口），
每次从摄像头读取一帧图片，
然后通过tld算法预测和处理该图片，把目标窗口画出来，
处理过后，显示该图像。
#include <opencv2/opencv.hpp>
#include <tld_utils.h>
#include <iostream>
#include <sstream>
#include <TLD.h>
#include <stdio.h>
using namespace cv;
using namespace std;
//Global variables
Rect box;
bool drawing_box = false;
bool gotBB = false;
bool tl = true;
bool rep = false;
bool fromfile=false;
string video;
/**
* 从一个文件中读出两个点的坐标，然后由这两点组成的box（矩形）
*/
void readBB(char* file){
ifstream bb_file (file);
string line;
getline(bb_file,line);
istringstream linestream(line);
string x1,y1,x2,y2;
getline (linestream,x1, ',');
getline (linestream,y1, ',');
getline (linestream,x2, ',');
getline (linestream,y2, ',');
int x = atoi(x1.c_str());// = (int)file["bb_x"];
int y = atoi(y1.c_str());// = (int)file["bb_y"];
int w = atoi(x2.c_str())-x;// = (int)file["bb_w"];
int h = atoi(y2.c_str())-y;// = (int)file["bb_h"];
box = Rect(x,y,w,h);
}
/**
*绑定鼠标事件
*/
//bounding box mouse callback
void mouseHandler(int event, int x, int y, int flags, void *param){
switch( event ){
case CV_EVENT_MOUSEMOVE:
if (drawing_box){
box.width = x-box.x;
box.height = y-box.y;
}
break;
case CV_EVENT_LBUTTONDOWN:
drawing_box = true;
box = Rect( x, y, 0, 0 );
break;
case CV_EVENT_LBUTTONUP:
drawing_box = false;
if( box.width < 0 ){
box.x += box.width;
box.width *= -1;
}
if( box.height < 0 ){
box.y += box.height;
box.height *= -1;
}
gotBB = true;
break;
}
}
void print_help(char** argv){
printf("use:\n %s -p /path/parameters.yml\n",argv[0]);
printf("-s source video\n-b bounding box file\n-tl track and learn\n-r repeat\n");
}
/**
* 解析命令行参数，该执行文件由很多种传参方式
* 其实只需要理解从parameters.yml读入参数就可以了
*/
void read_options(int argc, char** argv,VideoCapture& capture,FileStorage &fs){
for (int i=0;i<argc;i++){
if (strcmp(argv[i],"-b")==0){
if (argc>i){
readBB(argv[i+1]);
gotBB = true;
}
else
print_help(argv);
}
if (strcmp(argv[i],"-s")==0){
if (argc>i){
video = string(argv[i+1]);
capture.open(video);
fromfile = true;
}
else
print_help(argv);
}
if (strcmp(argv[i],"-p")==0){
if (argc>i){
fs.open(argv[i+1], FileStorage::READ);
}
else
print_help(argv);
}
if (strcmp(argv[i],"-no_tl")==0){
tl = false;
}
if (strcmp(argv[i],"-r")==0){
rep = true;
}
}
}
int main(int argc, char * argv[]){
VideoCapture capture;
capture.open(0);
FileStorage fs;
//Read options
read_options(argc,argv,capture,fs);//读参数
//fs.open("parameters.yml", FileStorage::READ);
//Init camera摄像头初始化
if (!capture.isOpened())
{
cout << "capture device failed to open!" << endl;
return 1;
}
//Register mouse callback to draw the bounding box
cvNamedWindow("TLD",CV_WINDOW_AUTOSIZE);
cvSetMouseCallback( "TLD", mouseHandler, NULL );
//TLD framework
TLD tld;
//Read parameters file
tld.read(fs.getFirstTopLevelNode());//把文件中的相关参数传到tld对象中
Mat frame;
Mat last_gray;
Mat first;
if (fromfile){
capture >> frame;
cvtColor(frame, last_gray, CV_RGB2GRAY);
frame.copyTo(first);
}else{
capture.set(CV_CAP_PROP_FRAME_WIDTH,340);
capture.set(CV_CAP_PROP_FRAME_HEIGHT,240);
}
///Initialization
GETBOUNDINGBOX:
while(!gotBB)
{
if (!fromfile){
capture >> frame;
}
else
first.copyTo(frame);
cvtColor(frame, last_gray, CV_RGB2GRAY);
drawBox(frame,box);
imshow("TLD", frame);
if (cvWaitKey(33) == 'q')
return 0;
}
if (min(box.width,box.height)<(int)fs.getFirstTopLevelNode()["min_win"]){
cout << "Bounding box too small, try again." << endl;
gotBB = false;
goto GETBOUNDINGBOX;
}
//Remove callback
cvSetMouseCallback( "TLD", NULL, NULL );
printf("Initial Bounding Box = x:%d y:%d h:%d w:%d\n",box.x,box.y,box.width,box.height);
//Output file
FILE *bb_file = fopen("bounding_boxes.txt","w");
//TLD initialization
tld.init(last_gray,box,bb_file);//tld初始化，参数为一个图像patch，目标box，保存box信息到bb_file
///Run-time
Mat current_gray;
BoundingBox pbox;
vector<Point2f> pts1;
vector<Point2f> pts2;
bool status=true;
int frames = 1;
int detections = 1;
REPEAT:
while(capture.read(frame)){//每读出一帧
//get frame
cvtColor(frame, current_gray, CV_RGB2GRAY);
//Process Frame
tld.processFrame(last_gray,current_gray,pts1,pts2,pbox,status,tl,bb_file);//用tld算法处理这一帧图像
//Draw Points
if (status){
drawPoints(frame,pts1);
drawPoints(frame,pts2,Scalar(0,255,0));
drawBox(frame,pbox);
detections++;
}
//Display显示被处理过后图像
imshow("TLD", frame);
//swap points and images
swap(last_gray,current_gray);
pts1.clear();
pts2.clear();
frames++;
printf("Detection rate: %d/%d\n",detections,frames);
char ch = cvWaitKey(33);
if ( ch== 'q')
break;
}
if (rep){
rep = false;
tl = false;
fclose(bb_file);
bb_file = fopen("final_detector.txt","w");
//capture.set(CV_CAP_PROP_POS_AVI_RATIO,0);
capture.release();
capture.open(video);
goto REPEAT;
}
fclose(bb_file);
return 0;
}
注：
原作者是用matlab实现的，我分析的源码是其他大神用c++和opencv实现的，源码可以从
https://github.com/arthurv/OpenTLD或者https://github.com/alantrrs/OpenTLD下载
本序列参考了zouxy09同学的序列文章，在此表示感谢
http://blog.csdn.net/zouxy09/article/details/7893011