I am writing a program that does the following in brief:
read YUV 4:2:0 frame from .yuv file
convert frame from YUV to RGB
make some operations on RGB frame
display the RGB frame
repeat the previous steps until there is no frame left in the .yuv file
I omitted the 3rd step currently, I do not make any operations on RGB frames right now. Because my program does not display the frame in correct colors.
Here is my code which is using OpenCV 2.1:
What is wrong with my code??
I also added pictures of actual colors and wrong colors of the first frame. Wrong colored picture is result of conversion from YUV to BGR (CV_YCrCb2BGR). But converting from YUV to RGB (CV_YCrCb2RGB) does not help, unfortunately.
int main()
{
int iFrameWidth = 640;
int iFrameHeight = 480;
.
.
.
FILE *fYUV0 = fopen( "C:\\YUV_Videos\\flamenco2_0.yuv", "rb" );
char *cFileBuffer0 = new char[ iFrameWidth*iFrameHeight*3/2 ];
IplImage *iplY420Frame = cvCreateImageHeader( cvSize(iFrameWidth , iFrameHeight ), IPL_DEPTH_8U, 1 );
IplImage *iplU420Frame = cvCreateImageHeader( cvSize(iFrameWidth/2, iFrameHeight/2), IPL_DEPTH_8U, 1 );
IplImage *iplV420Frame = cvCreateImageHeader( cvSize(iFrameWidth/2, iFrameHeight/2), IPL_DEPTH_8U, 1 );
IplImage *iplY444Frame = cvCreateImage( cvSize(iFrameWidth, iFrameHeight), IPL_DEPTH_8U, 1 );
IplImage *iplU444Frame = cvCreateImage( cvSize(iFrameWidth, iFrameHeight), IPL_DEPTH_8U, 1 );
IplImage *iplV444Frame = cvCreateImage( cvSize(iFrameWidth, iFrameHeight), IPL_DEPTH_8U, 1 );
IplImage *iplYUV444Frame = cvCreateImage( cvSize(iFrameWidth, iFrameHeight), IPL_DEPTH_8U, 3 );
IplImage *iplRGBFrame0 = cvCreateImage( cvSize(iFrameWidth, iFrameHeight), IPL_DEPTH_8U, 3 );
.
.
.
while( fread(cFileBuffer0, 1, iFrameWidth*iFrameHeight*3/2, fYUV0) )
{
cvSetData( iplY420Frame, cFileBuffer0, iFrameWidth );
cvSetData( iplU420Frame, cFileBuffer0 + iFrameWidth*iFrameHeight, iFrameWidth/2 );
cvSetData( iplV420Frame, cFileBuffer0 + iFrameWidth*iFrameHeight*5/4, iFrameWidth/2 );
cvResize( iplY420Frame, iplY444Frame );
cvResize( iplU420Frame, iplU444Frame );
cvResize( iplV420Frame, iplY444Frame );
cvMerge( iplY444Frame, iplU444Frame, iplV444Frame, NULL, iplYUV444Frame );
cvCvtColor( iplYUV444Frame, iplRGBFrame0, CV_YCrCb2BGR );
.
.
.
cvNamedWindow( "View0" );
cvShowImage( "View0", iplRGBFrame0 );
cvWaitKey( 1000/25 );
}//end-of-while
cvDestroyWindow( "View0" );
return 0;
}//end-of-main
Actual colors of the first frame, acquired from a YUV Player:
http://i59.tinypic.com/2n7ee6h.jpg
Wrong colors of the first frame, output of my program:
http://i58.tinypic.com/29lzcqp.jpg
I have found it! Actually it has been more than two weeks since I found it but here it is: I was resizing V component into Y component.
...
cvResize( iplY420Frame, iplY444Frame );
cvResize( iplU420Frame, iplU444Frame );
cvResize( iplV420Frame, iplY444Frame ); // iplY444Frame must be corrected as iplV444Frame
...
Lessons learned:
Never name variables with only one letter, words are always the best.
Related
I want to track an object in 2 images (Shot A, Shot B).
I know the location of the object in the first shot (ShotA) but I don't know the location of the object in the second shot (Shot B).
Shot A has multiple objects, so in order to track a specific object, I am selecting ROI of image where the object I want to track is. The problem is how do I track the features of that object in Shot B while keeping the same ROI size. Can I track the features of that object in the whole Image B without selecting an ROI?
This is the code I have. Currently it selects the same ROI of SHOTA in SHOTB, but sometimes the object in ROI of SHOTA is not in the ROI of SHOT B.
IplImage* imgA = cvLoadImage("52783180_RAW_OVR1.jpg",CV_LOAD_IMAGE_GRAYSCALE);
cvSetImageROI(imgA, cvRect(2300, 1700, 1000,1200));
cvNamedWindow("SHOTA",0);
cvShowImage("SHOTA", imgA);
//cvWaitKey(0);
CvSize img_sz = cvGetSize( imgA );
int win_size = 10;
IplImage* imgB = cvLoadImage("52783180_RAW_OVR2.jpg",CV_LOAD_IMAGE_GRAYSCALE);
cvSetImageROI(imgB, cvRect(2300, 1700, 1000,1200));
cvNamedWindow("SHOTB",0);
cvShowImage("SHOTB", imgB);
IplImage* imgC=cvLoadImage("52783180_RAW_OVR2.jpg",CV_LOAD_IMAGE_UNCHANGED);
cvSetImageROI(imgC, cvRect(2300, 1700, 1000,1200));
//cvNamedWindow("SHOTA",0);
//cvShowImage("SHOTA", imgA);
IplImage* eig_image = cvCreateImage( img_sz, IPL_DEPTH_32F, 1 );
IplImage* tmp_image = cvCreateImage( img_sz, IPL_DEPTH_32F, 1 );
int corner_count = MAX_CORNERS;
CvPoint2D32f* cornersA = new CvPoint2D32f[ MAX_CORNERS ];
//cvSetImageROI(imgA, cvRect(2300, 1700, 1000,1200));
cvGoodFeaturesToTrack(
imgA,
eig_image,
tmp_image,
cornersA,
&corner_count,
0.01,
5.0,
0,
3,
0,
0.04
);
//cvResetImageROI(imgA);
cvFindCornerSubPix(
imgA,
cornersA,
corner_count,
cvSize(win_size,win_size),
cvSize(-1,-1),
cvTermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS,20,0.03)
);
// Call the Lucas Kanade algorithm
//
char features_found[ MAX_CORNERS ];
float feature_errors[ MAX_CORNERS ];
CvSize pyr_sz = cvSize( imgA->width+8, imgB->height/3 );
IplImage* pyrA = cvCreateImage( pyr_sz, IPL_DEPTH_32F, 1 );
IplImage* pyrB = cvCreateImage( pyr_sz, IPL_DEPTH_32F, 1 );
CvPoint2D32f* cornersB = new CvPoint2D32f[ MAX_CORNERS ];
cvCalcOpticalFlowPyrLK(
imgA,
imgB,
pyrA,
pyrB,
cornersA,
cornersB,
corner_count,
cvSize( win_size,win_size ),
5,
features_found,
feature_errors,
cvTermCriteria( CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 20, .3 ),
0
);
// Now make some image of what we are looking at:
//
float sum=0;
for( int i=0; i<corner_count; i++ ) {
if( features_found[i]==0|| feature_errors[i]>550 ) {
// printf("Error is %f/n",feature_errors[i]);
continue;
}
sum+=(cornersA[i].x-cornersB[i].x)*(cornersA[i].x-cornersB[i].x)+(cornersA[i].y-cornersB[i].y)*(cornersA[i].y-cornersB[i].y);
// printf("Got it/n");
CvPoint p0 = cvPoint(
cvRound( cornersA[i].x ),
cvRound( cornersA[i].y )
);
CvPoint p1 = cvPoint(
cvRound( cornersB[i].x ),
cvRound( cornersB[i].y )
);
cvLine( imgC, p0, p1, CV_RGB(255,0,0),2 );
}
cvResetImageROI(imgC);
sum=sum/corner_count;
printf("%f\n",sum);
cvNamedWindow("ImageA",0);
cvNamedWindow("ImageB",0);
cvNamedWindow("LKpyr_OpticalFlow",0);
cvShowImage("ImageA",imgA);
cvShowImage("ImageB",imgB);
cvShowImage("LKpyr_OpticalFlow",imgC);
cvWaitKey(0);
Problem solved by using mask instead of setimageroi for GoodfeaturestoTrack
I am trying to write some simple real time face detection code, but somehow it doesn't work. (I tried face detection code on an image and it works but with the code below i get a grey image onscreen and the code fails)
here is the code i have tried (it prints 'face detected!' one time to the output window)
CvHaarClassifierCascade *cascade;
CvMemStorage *storage;
char *face_cascade="haarcascade_frontalface_alt2.xml";
CvRect* r;
const CvArr* img_size;
IplImage *grayscale;
void detectFacialFeatures( IplImage *img)
{
grayscale = cvCreateImage(cvGetSize(img), 8, 1);
cvCvtColor(img, grayscale, CV_BGR2GRAY);
CvMemStorage* storage=cvCreateMemStorage(0);
cvClearMemStorage( storage );
cvEqualizeHist(grayscale, grayscale);
cascade = ( CvHaarClassifierCascade* )cvLoad( face_cascade, 0, 0, 0 );
CvSeq* faces = cvHaarDetectObjects(grayscale, cascade, storage, 1.1, 3, CV_HAAR_DO_CANNY_PRUNING, cvSize( 50, 50 ) );
if(faces)
{
printf("face detected!");
r = ( CvRect* )cvGetSeqElem( faces, 0 );
cvRectangle( img,cvPoint( r->x, r->y ),cvPoint( r->x + r->width, r->y + r->height ), CV_RGB( 255, 0, 0 ), 1, 8, 0 );
}
}
int _tmain(int argc, _TCHAR* argv[])
{
int c;
IplImage* color_img;
CvCapture* cv_cap = cvCreateCameraCapture(0);
cvSetCaptureProperty(cv_cap, CV_CAP_PROP_FRAME_WIDTH, 640);
cvSetCaptureProperty(cv_cap, CV_CAP_PROP_FRAME_HEIGHT, 480);
cvNamedWindow("Video",1); // create window
for(;;) {
color_img = cvQueryFrame(cv_cap); // get frame
if(color_img==0)
break;
cvFlip(color_img, 0, 1); //mirror image
detectFacialFeatures(color_img);
cvShowImage("Video", color_img); // show frame
c = cvWaitKey(10); // wait 10 ms or for key stroke
if(c == 27)
break; // if ESC, break and quit
}
/* clean up */
cvReleaseCapture( &cv_cap );
cvDestroyWindow("Video");
}
Try without calling functions cvFlip and cvEqualizeHistogram.
Look at(just use cvShowImage) result of each operation(cvFlip, cvCvtColor, cvEqualizeHistogram) - it's possible that result of one of these operations is gray image.
You don't have to load haar classifier each time you try to find a face - load it at the beginning. Operations on files are slow so it should makes you code faster.
I try to run the following program according to what is written on this site
http://www.lirtex.com/robotics/fast-object-tracking-robot-computer-vision/
Initialization parameters
CvCapture *capture = cvCaptureFromCAM(0);
int width = ( int )cvGetCaptureProperty( capture, CV_CAP_PROP_FRAME_WIDTH );
int height = ( int )cvGetCaptureProperty( capture, CV_CAP_PROP_FRAME_HEIGHT );
IplImage *frame;
CvSize size = cvSize(640,480);
cvNamedWindow( "Camera", CV_WINDOW_NORMAL );
cvNamedWindow( "HSV", CV_WINDOW_NORMAL );
cvNamedWindow( "EdgeDetection", CV_WINDOW_NORMAL );
cvResizeWindow("Camera",640,480);
cvResizeWindow("HSV",640,480);
cvResizeWindow("EdgeDetection",640,480);
IplImage * hsv_frame = cvCreateImage(size, IPL_DEPTH_8U, 3);
IplImage* thresholded = cvCreateImage(size, IPL_DEPTH_8U, 1);
when im calling the function cvCvtColor like this:
cvCvtColor(frame, frame , CV_BGR2HSV);
with the 2nd paramter is equal to the first its work
but when im calling the function like this
cvCvtColor(frame, hsv_frame , CV_BGR2HSV);
its fail and throws an exception
Does anyone have any idea why this happens?
The Array frame is the size of the captured image whereas, *hsv_frame* has been hardcoded to 640x480. The colorspace conversion operation(cvCvtColor) requires that both the source and destination be of the same size and so the exception.
Solution:
a. Use the same size as the input by setting
CvSize size = cvSize(frame->width, frame->height);
-OR-
b. If you want the final o/p to be 640x480, resize the input to the required size using: cvResize
One final note: The C++ interface is much more intuitive, much more stable and has added features as compared to the C interface. I recommend moving to the C++ interface of OpenCV
I have implemented optical flow to track vehicles on road and it turned out to be very slow.
my code uses the functions:
cvGoodFeaturesToTrack
cvFindCornerSubPix
cvCalcOpticalFlowPyrLK
How do I make this tracking fast and efficient?
My code is:
#include "highgui.h"
#include "cv.h"
#include "cxcore.h"
#include <iostream>
using namespace std;
const int MAX_CORNERS = 500;
int main()
{
CvCapture* capture=cvCreateFileCapture("E:\cam1.avi");
IplImage* img_A;// = cvLoadImage("image0.png", CV_LOAD_IMAGE_GRAYSCALE);
IplImage* img_B;// = cvLoadImage("image1.png", CV_LOAD_IMAGE_GRAYSCALE);
img_A=cvQueryFrame(capture);
IplImage* imgA = cvCreateImage( cvGetSize(img_A), 8, 1 );
IplImage* imgB = cvCreateImage( cvGetSize(img_A), 8, 1 );
cvNamedWindow( "ImageA", CV_WINDOW_AUTOSIZE );
cvNamedWindow( "ImageB", CV_WINDOW_AUTOSIZE );
cvNamedWindow( "LKpyr_OpticalFlow", CV_WINDOW_AUTOSIZE );
while(1)
{
int couter=0;
for(int k=0;k<20;k++)
{
img_B=cvQueryFrame(capture);
}
//cvCvtColor(imgA,imgA,CV_BGR2GRAY);
//cvCvtColor(imgB,imgB,CV_BGR2GRAY);
// Load two images and allocate other structures
/*IplImage* imgA = cvLoadImage("image0.png", CV_LOAD_IMAGE_GRAYSCALE);
IplImage* imgB = cvLoadImage("image1.png", CV_LOAD_IMAGE_GRAYSCALE);*/
CvSize img_sz = cvGetSize( img_A );
int win_size = 10;
IplImage* imgC = cvCreateImage( cvGetSize(img_A), 8, 1 );
cvZero(imgC);
// Get the features for tracking
IplImage* eig_image = cvCreateImage( img_sz, IPL_DEPTH_32F, 1 );
IplImage* tmp_image = cvCreateImage( img_sz, IPL_DEPTH_32F, 1 );
int corner_count = MAX_CORNERS;
CvPoint2D32f* cornersA = new CvPoint2D32f[ MAX_CORNERS ];
cvCvtColor(img_A,imgA,CV_BGR2GRAY);
cvCvtColor(img_B,imgB,CV_BGR2GRAY);
cvGoodFeaturesToTrack( imgA, eig_image, tmp_image, cornersA, &corner_count ,0.05, 5.0, 0, 3, 0, 0.04 );
cvFindCornerSubPix( imgA, cornersA, corner_count, cvSize( win_size, win_size ) ,cvSize( -1, -1 ), cvTermCriteria( CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 20, 0.03 ) );
// Call Lucas Kanade algorithm
char features_found[ MAX_CORNERS ];
float feature_errors[ MAX_CORNERS ];
CvSize pyr_sz = cvSize( imgA->width+8, imgB->height/3 );
IplImage* pyrA = cvCreateImage( pyr_sz, IPL_DEPTH_32F, 1 );
IplImage* pyrB = cvCreateImage( pyr_sz, IPL_DEPTH_32F, 1 );
CvPoint2D32f* cornersB = new CvPoint2D32f[ MAX_CORNERS ];
/*int jk=0;
for(int i=0;i<imgA->width;i+=10)
{
for(int j=0;j<imgA->height;j+=10)
{
cornersA[jk].x=i;
cornersA[jk].y=j;
++jk;
}
}
*/
cvCalcOpticalFlowPyrLK( imgA, imgB, pyrA, pyrB, cornersA, cornersB, corner_count,
cvSize( win_size, win_size ), 5, features_found, feature_errors,
cvTermCriteria( CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 20, 0.3 ), 0 );
// Make an image of the results
for( int i=0; i < corner_count; i++ )
{
if( features_found[i]==0|| feature_errors[i]>550 )
{
//printf("Error is %f/n",feature_errors[i]);
continue;
}
//printf("Got it/n");
CvPoint p0 = cvPoint( cvRound( cornersA[i].x ), cvRound( cornersA[i].y ) );
CvPoint p1 = cvPoint( cvRound( cornersB[i].x ), cvRound( cornersB[i].y ) );
cvLine( imgC, p0, p1, CV_RGB(255,0,0), 2 );
cout<<p0.x<<" "<<p0.y<<endl;
}
cvShowImage( "LKpyr_OpticalFlow", imgC );
cvShowImage( "ImageA", imgA );
cvShowImage( "ImageB", imgB );
//cvCopyImage(imgB,imgA);
delete[] cornersA;
delete[] cornersB;
cvWaitKey(33);
}
return 0;
}
I might be going a bit over the line here but I would suggest you to check out OpenTLD. OpenTLD (aka Predator) is one of the most efficient tracking algorithm. Zdenek Kalal has implemented OpenTLD in MATLAB. George Nebehay has made a very efficient C++ OpenCV port of OpenTLD.
It's very easy to install and tracking is really efficient.
OpenTLD uses Median Flow Tracker to track and implements PN learning algorithm. In this YouTube Video, Zdenek Kalal shows the use of OpenTLD.
If you just want to implement a Median Flow Tracker, follow this link https://github.com/gnebehay/OpenTLD/tree/master/src/mftracker
If you want to use it in Python, I have made a Median Flow Tracker and also made a Python port of OpenTLD. But python port isn't much efficient.
First of all to track a car you have to somehow detect it (using color segmentation/background subtraction for example). When car is detected you have to track it (track some points on it) using cvCalcOpticalFlowPyrLK. I didn't find code that responces for car detection.
Take a look at this and this articles. Your idea should be the same.
Also your code is a bit wrong. For example why do you call cvGoodFeaturesToTrack in the main loop? You have to call it once - before loop to detect good features to track. But this will also detect non-cars.
Take a look at default OpenCV example: OpenCV/samples/cpp/lkdemo.cpp.
hey i tried to made a histogram that shows frames substraction, the code is running but i got gray window without result.
the message on the command window is:
Compiler did not align stack variables. Libavcodec has been miscompiled
and may be very slow or crash. This is not a bug in libavcodec,
but in the compiler. You may try recompiling using gcc >= 4.2.
Do not report crashes to FFmpeg developers.
OpenCV Error: Assertion failed (images[j].channels() == 1) in unknown function,
file ........\ocv\opencv\src\cv\cvhistogram.cpp, line 137
here is the code someone have an idea?thanks for help.....
int main()
{
int key = 0;
CvCapture* capture = cvCaptureFromAVI( "macroblock.mpg" );
IplImage* frame = cvQueryFrame( capture );
IplImage* currframe = cvCreateImage(cvGetSize(frame),IPL_DEPTH_8U,3);
IplImage* destframe = cvCreateImage(cvGetSize(frame),IPL_DEPTH_8U,3);
IplImage* imgHistogram = 0;
CvHistogram* hist;
if ( !capture )
{
fprintf( stderr, "Cannot open AVI!\n" );
return 1;
}
int fps = ( int )cvGetCaptureProperty( capture, CV_CAP_PROP_FPS );
cvNamedWindow( "dest", CV_WINDOW_AUTOSIZE );
cvNamedWindow( "imgHistogram", CV_WINDOW_AUTOSIZE );
while( key != 'x' )
{
frame = cvQueryFrame( capture );
currframe = cvCloneImage( frame );
frame = cvQueryFrame( capture );
cvSub(frame,currframe,destframe);
int bins = 256;
int hsize[] = {bins};
float max_value = 0, min_value = 0;
float value;
int normalized;
float xranges[] = {0, 256};
float* ranges[] = {xranges};
IplImage* planes[] = {destframe};
hist = cvCreateHist(1, hsize, CV_HIST_ARRAY, ranges,1);
cvCalcHist(planes, hist, 0, NULL);
cvGetMinMaxHistValue(hist, &min_value, &max_value);
// printf("Minimum Histogram Value: %f, Maximum Histogram Value: %f\n", min_value, max_value);
imgHistogram = cvCreateImage(cvSize(bins, 50),IPL_DEPTH_8U,3);
cvRectangle(imgHistogram, cvPoint(0,0), cvPoint(256,50), CV_RGB(255,255,255),-1);
for(int i=0; i < bins; i++){
value = cvQueryHistValue_1D(hist, i);
normalized = cvRound(value*50/max_value);
cvLine(imgHistogram,cvPoint(i,50), cvPoint(i,50-normalized), CV_RGB(0,0,0));
}
if(key==27 )break;
cvShowImage( "dest",destframe);
cvShowImage( "imgHistogram",imgHistogram);
key = cvWaitKey( 1000 / 10 );
}
cvDestroyWindow( "dest" );
cvReleaseCapture( &capture );
return 0;
}
Since you are trying to show a 1D histogram, the histogram plane needs to be in grayscale. So, you need to convert the resulting image from cvSub() to grayscale first. Try
IplImage *gray = NULL;
gray = cvCreateImage(cvGetSize(frame), IPL_DEPTH_8U, 1);
while(key != 'x') {
...
cvSub(frame, currframe, destframe);
cvCvtColor(destframe, gray, CV_BGR2GRAY);
...
IplImage* planes[] = {gray};
..
}
Let me know if it works for you.