OpenCV學習筆記十九---運動跟蹤 CamShift以及meanShift詳解

CamShift跟蹤器：

RotatedRect CamShift(InputArray probImage, Rect& window, TermCriteria criteria)

• probImage – 對象直方圖的反投影. 詳細見函數 calcBackProject() .
• window – 初始搜索窗口
• criteria – meanShift  停止迭代搜索標準.

meanShift跟蹤器：

int meanShift(InputArray probImage, Rect& window, TermCriteria criteria)

• probImage – Back projection of the object histogram. See calcBackProject() for details.
• window – Initial search window.
• criteria – Stop criteria for the iterative search algorithm.

計算直方圖的反投影：

void calcBackProject(const Mat* arrays, int narrays, const int* channels, InputArray hist, OutputArray backProject, const float** ranges, double scale=1, bool uniform=true )

• arrays – 源數組。它們都應該有相同的深度，CV_8U或CV_32F，和相同的大小。
• narrays – 源數組數
• channels – 用於計算反投影的通道列表。通道的數量必須與直方圖的維度相匹配。
• hist – 可以是密集或稀疏的輸入直方圖。
• backProject – 目標反投影是一個與數組array[0]相同大小和深度的單通道數組。.
• ranges – 查看函數 calcHist() .
• scale – 輸出反投影的可選比例因子。
• uniform – 指示直方圖是否是均勻的標誌

直接看程序中的講解吧：

#include <opencv2/video/tracking.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include <ctype.h>
using namespace std;
using namespace cv;
Mat image;
bool backprojMode = false;//表示是否進入反向投影模式，true表示進入反向投影模式
bool selectObject = false;//選擇要跟蹤的初始目標，true代表正在用鼠標選擇
int trackObject = 0;//代表目標跟蹤數量
bool showHist = true;//是否顯示直方圖
Point origin;  //保存鼠標選擇第一次單機時點的位置
Rect selection; //用於保存選擇的矩形框
int vmin = 10, vmax = 256, smin = 30;
void onMouse(int event, int x, int y, int, void*)
{
	if (selectObject) //通過鼠標左鍵按下去選擇矩形區域
	{
		selection.x = MIN(x, origin.x);//矩形頂點座標
		selection.y = MIN(y, origin.y);
		selection.width = std::abs(x - origin.x);//矩形寬
		selection.height = std::abs(y - origin.y);//矩形高

		selection &= Rect(0, 0, image.cols, image.rows);
	}
	switch (event)
	{
	case CV_EVENT_LBUTTONDOWN:
		origin = Point(x, y); //剛點擊時的點
		selection = Rect(x, y, 0, 0);
		selectObject = true; //正在用鼠標選擇
		break;
	case CV_EVENT_LBUTTONUP:
		selectObject = false; //鼠標停止選擇
		if (selection.width > 0 && selection.height > 0)
			trackObject = -1;
		break;
	}
}
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 =
{
	"{1|  | 0 | camera number}"
};

int main(int argc, const char** argv)
{
	help();
	VideoCapture cap; //定義一個攝像頭捕捉的類對象
	Rect trackWindow;
	RotatedRect trackBox; //定義一個旋轉的矩陣類對象
	int hsize = 16;
	float hranges[] = { 0, 180 };
	const float* phranges = hranges;
	CommandLineParser parser(argc, argv, keys); //命令解析器函數
	int camNum = parser.get<int>("1");
	cap.open(camNum);//直接調用成員函數打開攝像頭

	if (!cap.isOpened())
	{
		help();
		cout << "***Could not initialize capturing...***\n";
		cout << "Current parameter's value: \n";
		parser.printParams();
		return -1;
	}
	namedWindow("Histogram", 0);
	namedWindow("CamShift Demo", 0);
	setMouseCallback("CamShift Demo", onMouse, 0); //鼠標相應機制
	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;
	Mat histimg = Mat::zeros(200, 320, CV_8UC3), backproj;
	bool paused = false; 
	for (;;)
	{
		if (!paused)  //沒有暫停
		{
			cap >> frame;//從攝像頭抓取一幀圖像並輸出到frame中
			if (frame.empty())
				break;
		}
			
		frame.copyTo(image);
		if (!paused)
		{
			cvtColor(image, hsv, CV_BGR2HSV);
			if (trackObject)
			{
				int _vmin = vmin, _vmax = vmax;
				//利用了hsv的3個通道
				inRange(hsv, Scalar(0, smin, MIN(_vmin, _vmax)), Scalar(180, 256, MAX(_vmin, _vmax)), mask);
				int ch[] = { 0, 0 };
				//hue初始化爲與hsv大小深度一樣的矩陣，色調的度量是用角度表示的，紅綠藍之間相差120度，反色相差180度
				hue.create(hsv.size(), hsv.depth());
				mixChannels(&hsv, 1, &hue, 1, ch, 1);

				if (trackObject < 0)//鼠標選擇區域鬆開後，該函數內部又將其賦值1
				{
					//此處的構造函數roi用的時Mat hue的矩陣頭，且roi的數據指針指向hue
					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;

					histimg = Scalar::all(0);
					int binW = histimg.cols / hsize;
					Mat buf(1, hsize, CV_8UC3); //定義一個緩衝單bin矩陣
					for (int i = 0; i < hsize; i++)
						buf.at<Vec3b>(i) = Vec3b(saturate_cast<uchar>(i*180. / hsize), 255, 255);
					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);
				backproj &= mask;

				trackBox = CamShift(backproj, trackWindow, TermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1));
				//meanShift(backproj, trackWindow, TermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1));
				if (trackWindow.area() <= 1)
				{
					int cols = backproj.cols, rows = backproj.rows;
					int 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);
				//rectangle(image, Point(trackWindow.x, trackWindow.y), Point(trackWindow.x + trackWindow.width, trackWindow.y + trackWindow.height), Scalar(0, 0, 255), -1, CV_AA);


			}
		}
		//後面代碼不管pause爲真還是假都是要執行的
		else if (trackObject < 0)  //同時也是在按了暫停字母之後
			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;
		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;
}

meanShift與CamShift函數不同的一點是，它返回的不是一個矩形框，而是一個int型變量。該int型變量應該是代表找到目標物體的個數。特別需要注意的是參數window，它不僅是目標物體初始化的位置，還是實時跟蹤目標後的位置，所以其實也是一個返回值。由於meanShift好像主要不是用於目標跟蹤上，很多應用是在圖像分割上。但是這裏還是將CamShift算法例子稍微改一下，就成了meanShift算法了。

//meanShift(backproj, trackWindow, TermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1));
trackBox = CamShift(backproj, trackWindow, TermCriteria(CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1));

這個就是代碼中兩者跟蹤的區別，CamShift可以根據遠離攝像機時的目標大小自動調節窗口的大小，而meanShift不能調節。