CamShfit跟踪例程解析

CamShift的原理还是比较简单的，跟踪直方图特征搜索出目标进行跟踪，相对于meanShift，解决的尺度问题。

代码如下：

#include "opencv2/video/tracking.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/highgui/highgui.hpp"

#include <iostream>
#include <ctype.h>

using namespace cv;
using namespace std;

Mat image;

bool backprojMode = false;
bool selectObject = false;
int trackObject = 0;
bool showHist = true;
Point origin;
Rect selection;
int vmin = 10, vmax = 256, smin = 30;

static void onMouse( int event, int x, int y, int, void* )
{
	if( selectObject )////只有当鼠标左键按下去时才有效，然后通过if里面代码就可以确定所选择的矩形区域selection了

	{
		selection.x = MIN(x, origin.x);//矩形左上角顶点坐标
		selection.y = MIN(y, origin.y);
		selection.width = std::abs(x - origin.x);//矩形宽
		selection.height = std::abs(y - origin.y);//矩形高

		selection &= Rect(0, 0, image.cols, image.rows);//用于确保所选的矩形区域在图片范围内

	}

	switch( event )
	{
	case CV_EVENT_LBUTTONDOWN:
		origin = Point(x,y);//鼠标初始点击坐标
		selection = Rect(x,y,0,0);//鼠标刚按下去时初始化了一个矩形区域

		selectObject = true;
		break;
	case CV_EVENT_LBUTTONUP:
		selectObject = false;
		if( selection.width > 0 && selection.height > 0 )
			trackObject = -1;
		break;
	}
}

static void help()
{
	cout << "\nThis is a demo that shows mean-shift based tracking\n"
		"You select a color objects such as your face and it tracks it.\n"
		"This reads from video camera (0 by default, or the camera number the user enters\n"
		"Usage: \n"
		"   ./camshiftdemo [camera number]\n";

	cout << "\n\nHot keys: \n"
		"\tESC - quit the program\n"
		"\tc - stop the tracking\n"
		"\tb - switch to/from backprojection view\n"
		"\th - show/hide object histogram\n"
		"\tp - pause video\n"
		"To initialize tracking, select the object with mouse\n";
}

const char* keys =
{
	"{c| camero | 0 | camera number}" //简称 | 全称 |值 |帮助说明
	"{f| file   | F:/.mp4 | open avi files}"
};

int main( int argc, const char** argv )
{

	
	help();

	VideoCapture cap;
	Rect trackWindow;//跟踪窗的大小
	int hsize = 16;
	float hranges[] = {0,180}; //直方图的范围
	const float* phranges = hranges;
	CommandLineParser parser(argc, argv, keys);//命令行解析器
	int camNum = parser.get<int>("c");

	

	cap.open(camNum);
	parser.printParams();
	if( !cap.isOpened() )
	{
		help();
		cout << "***Could not initialize capturing...***\n";
		cout << "Current parameter's value: \n";
		parser.printParams();  //打印出keys 
		return -1;
	}
	
	namedWindow( "Histogram", 0 );
	namedWindow( "CamShift Demo", 0 );
	setMouseCallback( "CamShift Demo", onMouse, 0 );
	createTrackbar( "Vmin", "CamShift Demo", &vmin, 256, 0 );
	createTrackbar( "Vmax", "CamShift Demo", &vmax, 256, 0 );
	createTrackbar( "Smin", "CamShift Demo", &smin, 256, 0 );

	Mat frame, hsv, hue, mask, hist, histimg = Mat::zeros(200, 320, CV_8UC3), backproj;
	bool paused = false;
	for(;;)
	{
		if( !paused )  //多个相同条件的If语句，可以同步进行好几步操作
		{
			cap >> frame;
			if( frame.empty() )
				break;
		}

		frame.copyTo(image); //多个相同条件的If语句，可以同步进行好几步操作

		if( !paused )
		{
			cvtColor(image, hsv, CV_BGR2HSV);

			if( trackObject )
			{
				int _vmin = vmin, _vmax = vmax;

				//inRange函数的功能是检查输入数组每个元素大小是否在2个给定数值之间，可以有多通道,mask保存0通道的最小值，也就是h分量
				//这里利用了hsv的3个通道，比较h,0~180,s,smin~256,v,min(vmin,vmax),max(vmin,vmax)。如果3个通道都在对应的范围内，则
				//mask对应的那个点的值全为1(0xff)，否则为0(0x00).
				inRange(hsv, Scalar(0, smin, MIN(_vmin,_vmax)),
					Scalar(180, 256, MAX(_vmin, _vmax)), mask);

				int ch[] = {0, 0};//洗牌规则
				hue.create(hsv.size(), hsv.depth());
				mixChannels(&hsv, 1, &hue, 1, ch, 1);////将hsv第一个通道(也就是色调)的数复制到hue中，0索引数组
				//setMouseCallback( "CamShift Demo", NULL, 0 );  //注销鼠标事件
				if( trackObject < 0 )//鼠标选择区域松开后，该函数内部又将其赋值1

				{   
					//此处的构造函数roi用的是Mat hue的矩阵头，且roi的数据指针指向hue，即共用相同的数据，
					//select为其感兴趣的区域
					////mask保存的hsv的最小值

					Mat roi(hue, selection), maskroi(mask, selection);
					calcHist(&roi, 1, 0, maskroi, hist, 1, &hsize, &phranges);
					normalize(hist, hist, 0, 255, CV_MINMAX);

					trackWindow = selection;
					trackObject = 1;//只要鼠标选完区域松开后，且没有按键盘清0键'c'，则trackObject一直保持为1，
					               //因此该if函数只能执行一次，除非重新选择跟踪区域

					//histimg是直方图图像
					histimg = Scalar::all(0);//与按下'c'键是一样的，这里的all(0)表示的是标量全部清0
					int binW = histimg.cols / hsize;

					Mat buf(1, hsize, CV_8UC3);//定义一个缓冲单bin矩阵，不同的bin画出不同颜色
					for( int i = 0; i < hsize; i++ )
						buf.at<Vec3b>(i) = Vec3b(saturate_cast<uchar>(i*180./hsize), 255, 255);//saturate_case函数为从一个初始类型准确变换到另一个初始类型
					cvtColor(buf, buf, CV_HSV2BGR);

					for( int i = 0; i < hsize; i++ )
					{
						int val = saturate_cast<int>(hist.at<float>(i)*histimg.rows/255);
						rectangle( histimg, Point(i*binW,histimg.rows),
							Point((i+1)*binW,histimg.rows - val),
							Scalar(buf.at<Vec3b>(i)), -1, 8 );
					}
				}

				calcBackProject(&hue, 1, 0, hist, backproj, &phranges);
				//imshow("backproj",backproj);
				//waitKey(20);


				backproj &= mask; //超出范围的置零


				//opencv2.0以后的版本函数命名前没有cv两字了，并且如果函数名是由2个意思的单词片段组成的话，
				//且前面那个片段不够成单词，则第一个字母要
				//大写，比如Camshift，如果第一个字母是个单词，则小写，比如meanShift，但是第二个字母一定要大写
				RotatedRect trackBox = CamShift(backproj, trackWindow,
					TermCriteria( CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1 ));
				if( trackWindow.area() <= 1 )
				{
					int cols = backproj.cols, rows = backproj.rows, r = (MIN(cols, rows) + 5)/6;
					trackWindow = Rect(trackWindow.x - r, trackWindow.y - r,
						trackWindow.x + r, trackWindow.y + r) &
						Rect(0, 0, cols, rows);
				}

				if( backprojMode )
					cvtColor( backproj, image, CV_GRAY2BGR );
				ellipse( image, trackBox, Scalar(0,0,255), 3, CV_AA );
			}
		}
		else if( trackObject < 0 )
			paused = false;

		if( selectObject && selection.width > 0 && selection.height > 0 )
		{
			Mat roi(image, selection);
			bitwise_not(roi, roi);
		}

		imshow( "CamShift Demo", image );
		imshow( "Histogram", histimg );

		char c = (char)waitKey(10);
		if( c == 27 )
			break;
		switch(c)
		{
		case 'b':
			backprojMode = !backprojMode;
			break;
		case 'c':
			trackObject = 0;
			histimg = Scalar::all(0);
			break;
		case 'h':
			showHist = !showHist;
			if( !showHist )
				destroyWindow( "Histogram" );
			else
				namedWindow( "Histogram", 1 );
			break;
		case 'p':
			paused = !paused;
			break;
		default:
			;
		}
	}

	return 0;
}

一下是上面程序涉及到的几个函数的用法的简单测试代码，以了解，函数的特性

包括 Mat(const Mat& m, const Rect& roi)用法测试，saturate_cast函数测试，RotatedRect类型测试代码，mixChannels用法测试

 

#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/highgui/highgui.hpp"
#include <iostream>
#include <ctype.h>

using namespace cv;
using namespace std;

int main()
{   
	//Mat感兴趣区域设置， Mat(const Mat& m, const Rect& roi)用法测试
	// 即： creates a matrix header for a part of the bigger matrix
	Mat img=imread("./longtan.jpg");
	Rect roi(100,100,100,100);
	Mat img_roi(img,roi);//感兴趣区域选择，img_roi和img共用一个矩阵头，指向相同的值区域

	namedWindow("img", WINDOW_AUTOSIZE);
	namedWindow("img_roi",WINDOW_AUTOSIZE);

	cout<<"img.cols ="<<endl<<img.cols<<endl;
	cout<<"img.rows="<<endl<<img.rows<<endl;

	cout<<"img_roi.cols ="<<endl<<img_roi.cols<<endl;
	cout<<"img_roi.rows="<<endl<<img_roi.rows<<endl;


	imshow("img",img);
	imshow("img_roi",img_roi);

	//saturate_cast函数为从一个初始类型准确变换到另一个初始类型
	//类似于STL中static_cast，是保留范围内有效值的舍去，而不是武断的直接阶段
	uchar a = saturate_cast<uchar>(-100); // a = 0 (UCHAR_MIN)安全转换
	short b = saturate_cast<short>(33333.33333); // b = 32767 (SHRT_MAX)

	cout<<"a ="<<endl<<(int)a<<endl;
	cout<<"b ="<<endl<<b<<endl;

	//RotatedRect类型测试代码，用于表达可旋转的矩形
	Mat image(200, 200, CV_8UC3, Scalar(0));
	RotatedRect rRect = RotatedRect(Point2f(100,100), Size2f(100,50),80);
	Point2f vertices[4];
	rRect.points(vertices);
	for (int i = 0; i < 4; i++)
		line(image, vertices[i], vertices[(i+1)%4], Scalar(0,255,0));
	Rect brect = rRect.boundingRect();
	rectangle(image, brect, Scalar(255,0,0));
	imshow("rectangles", image);

	//mixChannels用法测试，Split等函数是它的一个特例，
	//可以根据你的需要从一个Mat中以何种顺序分裂出哪个通道,到指定Mat，可以又一个Mat分裂出若干Mat
	Mat rgba( 4, 4, CV_8UC4, Scalar(1,2,3,4) );
	cout<<"rgba ="<<endl<<rgba<<endl;
	Mat bgr( rgba.rows, rgba.cols, CV_8UC3 );
	Mat alpha( rgba.rows, rgba.cols, CV_8UC1 );
	// forming an array of matrices is a quite efficient operation,
	// because the matrix data is not copied, only the headers
	Mat out[] = { bgr, alpha };//注意out[]的含义，分裂到一个Mat数组中
	// rgba[0] -> bgr[2], rgba[1] -> bgr[1],
	// rgba[2] -> bgr[0], rgba[3] -> alpha[0]
	int from_to[] = { 0,2, 1,1, 2,0, 3,3 };//指定分裂规则
	mixChannels( &rgba, 1, out, 2, from_to, 4 );

	cout<<"bgr ="<<endl<<bgr<<endl;
	cout<<"alpha ="<<endl<<alpha<<endl;

	waitKey(0); //有imshow的最好都加上这句，对于视频帧则必须加上，以给预留窗口刷新时间，不然会卡死
}