[opencv] lk光流法小结

本文记录了LK光流法的原理和opencv的使用实例。

一、理论部分

参考：http://www.cnblogs.com/andyanut/p/5893168.html

二、在opencv中的使用

void cvCalcOpticalFlowPyrLK(  
                            const CvArr* prev,  
                            const CvArr* curr,  
                            CvArr* prevPyr,  
                            CvArr* currPyr,  
                            const CvPoint2D32f* prevFeatures,  
                            CvPoint2D32f* currFeatures,  
                            int count,  
                            CvSize winSize,  
                            int level,  
                            char* status,  
                            float* track error,  
                            CvTermCriteria criteria,  
                            int flags );

参数介绍：

prevImg – first 8-bit input image or pyramid constructed by buildOpticalFlowPyramid(). 第一个8位输入图像或者通过 buildOpticalFlowPyramid()建立的金字塔 nextImg – second input image or pyramid of the same size and the same type as prevImg. 第二个输入图像或者和prevImg相同尺寸和类型的金字塔 prevPts – vector of 2D points for which the flow needs to be found; point coordinates must be single-precision floating-point numbers. 二维点向量存储找到的光流；点坐标必须是单精度浮点数 nextPts – output vector of 2D points (with single-precision floating-point coordinates) containing the calculated new positions of input features in the second image; when OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input. 输出二维点向量（用单精度浮点坐标）包括第二幅图像中计算的输入特征的新点位置；当OPTFLOW_USE_INITIAL_FLOW 标志通过，向量必须有和输入一样的尺寸。 status – output status vector (of unsigned chars); each element of the vector is set to 1 if the flow for the corresponding features has been found, otherwise, it is set to 0. 输出状态向量（无符号char）；如果相应的流特征被发现，向量的每个元素被设置为1，否则，被置为0. err – output vector of errors; each element of the vector is set to an error for the corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn’t found then the error is not defined (use the status parameter to find such cases). 输出错误向量；向量的每个元素被设为相应特征的一个错误，误差测量的类型可以在flags参数中设置；如果流不被发现然后错误未被定义（使用status（状态）参数找到此情形）。 winSize – size of the search window at each pyramid level. 在每个金字塔水平搜寻窗口的尺寸。 maxLevel – 0-based maximal pyramid level number; if set to 0, pyramids are not used (single level), if set to 1, two levels are used, and so on; if pyramids are passed to input then algorithm will use as many levels as pyramids have but no more than maxLevel. criteria – parameter, specifying the termination criteria of the iterative search algorithm (after the specified maximum number of iterations criteria.maxCount or when the search window moves by less than criteria.epsilon. flags – operation flags: OPTFLOW_USE_INITIAL_FLOW uses initial estimations, stored in nextPts; if the flag is not set, then prevPts is copied to nextPts and is considered the initial estimate. OPTFLOW_LK_GET_MIN_EIGENVALS use minimum eigen values as an error measure (seeminEigThreshold description); if the flag is not set, then L1 distance between patches around the original and a moved point, divided by number of pixels in a window, is used as a error measure. minEigThreshold – the algorithm calculates the minimum eigen value of a 2x2 normal matrix of optical flow equations (this matrix is called a spatial gradient matrix in [Bouguet00]), divided by number of pixels in a window; if this value is less than minEigThreshold, then a corresponding feature is filtered out and its flow is not processed, so it allows to remove bad points and get a performance boost.

函数示例：

下面的程序实现了利用LK光流法对视频中的运动目标进行跟踪

#include 
#include 
#include 
#include 
#include 
#include 

using namespace std;
using namespace cv;

void tracking(Mat &frame, Mat &output);
bool addNewPoints();
bool acceptTrackedPoint(int i);

string window_name = "optical flow tracking";
Mat gray;	// 当前图片
Mat gray_prev;	// 预测图片
vector points[2];	// point0为特征点的原来位置，point1为特征点的新位置
vector initial;	// 初始化跟踪点的位置
vector features;	// 检测的特征
int maxCount = 500;		// 检测的最大特征数
double qLevel = 0.01;	// 特征检测的等级
double minDist = 10.0;	// 两特征点之间的最小距离
vector status;	// 跟踪特征的状态，特征的流发现为1，否则为0
vector err;
int main()
{
	Mat frame;
	Mat result;

	VideoCapture capture("E:\\data\\hog_svm\\pedestrian.avi");

	if (capture.isOpened()/*capture*/)	// 摄像头读取文件开关
	{
		while (true)
		{
			capture >> frame;

			if (!frame.empty())
			{
				tracking(frame, result);
			}
			else
			{
				printf(" --(!) No captured frame -- Break!");
				break;
			}

			int c = waitKey(100);
			if ((char)c == 27)
			{
				break;
			}
		}
	}
	return 0;
}

//////////////////////////////////////////////////////////////////////////
// function: tracking
// brief: 跟踪
// parameter: frame	输入的视频帧
//			  output 有跟踪结果的视频帧
// return: void
//////////////////////////////////////////////////////////////////////////
void tracking(Mat &frame, Mat &output)
{
	cvtColor(frame, gray, CV_BGR2GRAY);
	frame.copyTo(output);
	// 添加特征点
	if (addNewPoints())
	{
		goodFeaturesToTrack(gray, features, maxCount, qLevel, minDist);
		points[0].insert(points[0].end(), features.begin(), features.end());
		initial.insert(initial.end(), features.begin(), features.end());
	}

	if (gray_prev.empty())
	{
		gray.copyTo(gray_prev);
	}
	// l-k光流法运动估计
	calcOpticalFlowPyrLK(gray_prev, gray, points[0], points[1], status, err);
	// 去掉一些不好的特征点
	int k = 0;
	for (size_t i = 0; i 2);
}

prevImg – first 8-bit input image or pyramid constructed by buildOpticalFlowPyramid(). 第一个8位输入图像或者通过 buildOpticalFlowPyramid()建立的金字塔 nextImg – second input image or pyramid of the same size and the same type as prevImg. 第二个输入图像或者和prevImg相同尺寸和类型的金字塔 prevPts – vector of 2D points for which the flow needs to be found; point coordinates must be single-precision floating-point numbers. 二维点向量存储找到的光流；点坐标必须是单精度浮点数 nextPts – output vector of 2D points (with single-precision floating-point coordinates) containing the calculated new positions of input features in the second image; when OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input. 输出二维点向量（用单精度浮点坐标）包括第二幅图像中计算的输入特征的新点位置；当OPTFLOW_USE_INITIAL_FLOW 标志通过，向量必须有和输入一样的尺寸。 status – output status vector (of unsigned chars); each element of the vector is set to 1 if the flow for the corresponding features has been found, otherwise, it is set to 0. 输出状态向量（无符号char）；如果相应的流特征被发现，向量的每个元素被设置为1，否则，被置为0. err – output vector of errors; each element of the vector is set to an error for the corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn’t found then the error is not defined (use the status parameter to find such cases). 输出错误向量；向量的每个元素被设为相应特征的一个错误，误差测量的类型可以在flags参数中设置；如果流不被发现然后错误未被定义（使用status（状态）参数找到此情形）。 winSize – size of the search window at each pyramid level. 在每个金字塔水平搜寻窗口的尺寸。 maxLevel – 0-based maximal pyramid level number; if set to 0, pyramids are not used (single level), if set to 1, two levels are used, and so on; if pyramids are passed to input then algorithm will use as many levels as pyramids have but no more than maxLevel. criteria – parameter, specifying the termination criteria of the iterative search algorithm (after the specified maximum number of iterations criteria.maxCount or when the search window moves by less than criteria.epsilon. flags – operation flags: OPTFLOW_USE_INITIAL_FLOW uses initial estimations, stored in nextPts; if the flag is not set, then prevPts is copied to nextPts and is considered the initial estimate. OPTFLOW_LK_GET_MIN_EIGENVALS use minimum eigen values as an error measure (seeminEigThreshold description); if the flag is not set, then L1 distance between patches around the original and a moved point, divided by number of pixels in a window, is used as a error measure. minEigThreshold – the algorithm calculates the minimum eigen value of a 2x2 normal matrix of optical flow equations (this matrix is called a spatial gradient matrix in [Bouguet00]), divided by number of pixels in a window; if this value is less than minEigThreshold, then a corresponding feature is filtered out and its flow is not processed, so it allows to remove bad points and get a performance boost.