嘿， 我正在做一个项目，通过使用光流方法来稳定视频序列。 到目前为止我已经把光流做得很好了。但我面前有两个分支可以处理它。 1-获得光流后，我找到了图像位移的平均值，然后我从第二帧的特征中减去了平均值，我的问题是下一步做什么？
2-或者我可以使用 openCV 函数来稳定图像，我计算了变换矩阵，然后使用 cvPerspectiveTransform 然后 cvWarpPerspective，但我收到错误，这是“坏标志”
你可以看代码，我想要的是如何稳定图像？我想知道你能提供什么解决方案吗？
enter code here
#include <stdio.h>
#include <stdlib.h>
//#include "/usr/include/opencv/cv.h"
#include <cv.h>
#include <cvaux.h>
#include <highgui.h>
#include <math.h>
#include <iostream>
#define PI 3.1415926535898
double rads(double degs)
{
return (PI/180 * degs);
}
CvCapture *cap;
IplImage *img;
IplImage *frame;
IplImage *frame1;
IplImage *frame3;
IplImage *frame2;
IplImage *temp_image1;
IplImage *temp_image2;
IplImage *frame1_1C;
IplImage *frame2_1C;
IplImage *eig_image;
IplImage *temp_image;
IplImage *pyramid1 = NULL;
IplImage *pyramid2 = NULL;
char * mapx;
char * mapy;
int h;
int corner_count;
CvMat* M = cvCreateMat(3,3,CV_32FC1);
CvPoint p,q,l,s;
double hypotenuse;
double angle;
int line_thickness = 1, line_valid = 1, pos = 0;
CvScalar line_color;
CvScalar target_color[4] = { // in BGR order
{{ 0, 0, 255, 0 }}, // red
{{ 0, 255, 0, 0 }}, // green
{{ 255, 0, 0, 0 }}, // blue
{{ 0, 255, 255, 0 }} // yellow
};
inline static double square(int a)
{
return a * a;
}
char* IntToChar(int num){return NULL;}
/*{
char* retstr = static_cast<char*>(calloc(12, sizeof(char)));
if (sprintf(retstr, "%i", num) > 0)
{
return retstr;
}
else
{
return NULL;
}
}*/
inline static void allocateOnDemand( IplImage **img, CvSize size, int depth, int channels )
{
if ( *img != NULL )
return;
*img = cvCreateImage( size, depth, channels );
if ( *img == NULL )
{
fprintf(stderr, "Error: Couldn't allocate image. Out of memory?\n");
exit(-1);
}
}
void clearImage (IplImage *img)
{
for (int i=0; i<img->imageSize; i++)
img->imageData[i] = (char) 0;
}
int main()
{
cap = cvCaptureFromCAM(0);
//cap = cvCaptureFromAVI("/home/saif/Desktop/NAO.. the project/jj/Test3.avi");
CvSize frame_size;
// Reading the video's frame size
frame_size.height = (int) cvGetCaptureProperty( cap, CV_CAP_PROP_FRAME_HEIGHT );
frame_size.width = (int) cvGetCaptureProperty( cap, CV_CAP_PROP_FRAME_WIDTH );
cvNamedWindow("Optical Flow", CV_WINDOW_AUTOSIZE);
while(true)
{
frame = cvQueryFrame( cap );
if (frame == NULL)
{
fprintf(stderr, "Error: Hmm. The end came sooner than we thought.\n");
return -1;
}
// Allocating another image if it is not allocated already.
allocateOnDemand( &frame1_1C, frame_size, IPL_DEPTH_8U, 1 );
cvConvertImage(frame, frame1_1C, 0);
allocateOnDemand( &frame1, frame_size, IPL_DEPTH_8U, 3 );
cvConvertImage(frame, frame1, 0);
//Get the second frame of video.
frame = cvQueryFrame( cap );
if (frame == NULL)
{
fprintf(stderr, "Error: Hmm. The end came sooner than we thought.\n");
return -1;
}
if(!frame)
{
printf("bad video \n");
exit(0);
}
allocateOnDemand( &frame2_1C, frame_size, IPL_DEPTH_8U, 1 );
cvConvertImage(frame, frame2_1C, 0);
allocateOnDemand( &frame2, frame_size, IPL_DEPTH_8U, 3 );
cvConvertImage(frame, frame2, 0);
CvSize optical_flow_window = cvSize(5,5);
eig_image = cvCreateImage( frame_size, IPL_DEPTH_32F, 1 );
temp_image = cvCreateImage( frame_size, IPL_DEPTH_32F, 1 );
CvTermCriteria optical_flow_termination_criteria = cvTermCriteria( CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 20, .3 );
// Feature tracking
CvPoint2D32f frame1_features[4];
CvPoint2D32f frame2_features[4];
//cvCornerEigenValsAndVecs(eig_image, temp_image, 1 );
corner_count = 4;
cvGoodFeaturesToTrack(frame1_1C,eig_image , temp_image, frame1_features, &corner_count, 0.1, .01, NULL, 5, 1);
cvFindCornerSubPix( frame1_1C, frame1_features, corner_count,cvSize(5, 5) ,optical_flow_window , optical_flow_termination_criteria);
if ( corner_count <= 0 )
printf( "\nNo features detected.\n" );
else
printf( "\nNumber of features found = %d\n", corner_count );
//Locus Kande method.
char optical_flow_found_feature[20];
float optical_flow_feature_error[20];
allocateOnDemand( &pyramid1, frame_size, IPL_DEPTH_8U, 1 );
allocateOnDemand( &pyramid2, frame_size, IPL_DEPTH_8U, 1 );
cvCalcOpticalFlowPyrLK(frame1_1C, frame2_1C, pyramid1, pyramid2, frame1_features, frame2_features, corner_count, optical_flow_window, 5, optical_flow_found_feature, NULL, optical_flow_termination_criteria, NULL);
/*
double sumOfDistancesX = 0;
double sumOfDistancesY = 0;
int debug = 0;
CvFont font1, font2;
CvScalar red, green, blue;
IplImage* seg_in = NULL;
IplImage *seg_out = NULL;
allocateOnDemand( &seg_in, frame_size, IPL_DEPTH_8U, 3 );
allocateOnDemand( &seg_out, frame_size, IPL_DEPTH_8U, 3 );
clearImage(seg_in);
clearImage(seg_in);
for( int i=0; i <corner_count; i++ )
{
if ( optical_flow_found_feature[i] == 0 )
continue;
p.x = (int) frame1_features[i].x;
p.y = (int) frame1_features[i].y;
q.x = (int) frame2_features[i].x;
q.y = (int) frame2_features[i].y;
angle = atan2( (double) p.y - q.y, (double) p.x - q.x );
sumOfDistancesX += q.x - p.x;
sumOfDistancesY += q.y - p.y;
//cvRemap(frame2,frame1,averageDistanceX , averageDistanceY,CV_INTER_LINEAR | CV_WARP_FILL_OUTLIERS, cvScalarAll(0));
}
*/
/*
int averageDistanceX = sumOfDistancesX / corner_count;
int averageDistanceY = sumOfDistancesY / corner_count;
l.x = averageDistanceX - q.x;
s.y = averageDistanceY - q.y;
*/
#define cvWarpPerspectiveQMatrix cvGetPerspectiveTransform
//CvMat* N = cvCreateMat(3,3,CV_32FC1);
cvGetPerspectiveTransform(frame2_features, frame1_features, M);
cvPerspectiveTransform(frame1_features, frame2_features, M);
cvWarpPerspective( frame2_features, frame1_features, M,CV_INTER_LINEAR+CV_WARP_FILL_OUTLIERS,cvScalarAll(0) );
cvShowImage("Optical Flow", frame1);
cvWaitKey(50);
}
cvReleaseCapture(&cap);
cvReleaseMat(&M);
return 0;
}
最佳答案
您不想从第二个图像中减去平均位移，而是想通过平均位移来变换(移动)第二个图像，以便它“匹配”第一个图像。您使用的“位移”取决于您的情况。
- 如果您的相机在晃动但静止，否则您希望使用两个连续帧之间的平均位移作为第二帧的变换 vector 。对于每个新帧，您计算变换后的第一帧和新帧之间的位移，并变换新帧。
- 如果您的相机移动并晃动(即山地自行车 Helm 上安装的相机)，您需要首先找到几帧内帧之间的平均位移，然后根据该平均位移与平均位移之间的差异来转换序列中的各个帧。它与前一帧之间的位移。
编辑 对于选项 2，您基本上需要做的是计算最后几帧中帧之间的平均运动的平均值。您可以通过多种方式做到这一点，但我建议使用卡尔曼滤波器之类的东西。然后，对于新帧，您可以计算该帧与(校正后的)前一帧之间的移动。从您获得的运动中减去到该点的平均运动，然后将新帧移动该差值。
关于c++ - 图像稳定，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/4247700/