OpenCV: Issues in using color frames with SURF features - visual-studio-2010

Question

I am trying to work with this code so that SURF can be implemented using color frames/images and then use the code here Kalman_Color_Object_Trackto track the detected object using the color value by Kalman filter. So, these are the steps that I intend to do but I am stuck since this SURF detection code does not accept/work with color images:
"book1.png" is the color image
After the rectangle around the image is detected from the incoming frames, the Mat structure is changed to IplImage since the Kalman_Color_Object_Track code is in C++ by
dest_image=cvCloneImage(&(IplImage)image);
mat_frame=cvCloneImage(&(IplImage)frame);
Call the Kalman_Color_Object_Track( mat_frame,dest_image,30); method.
Questions : (A) How to make this code work so that SURF features can be extracted and detected for color images? (B) I am unsure what should be passed in the function signature of Kalman_Color_Object_Track() and (C) where exactly in the object detection module should it be called?
#include <stdio.h>
#include <iostream>
#include "opencv2/core/core.hpp"
#include "opencv2/features2d/features2d.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/calib3d/calib3d.hpp"
using namespace cv;
IplImage *mat_dest_image=0;
IplImage *mat_frame=0;
/* Object Detection and recognition from video*/
int main()
{
Mat object = imread( "book1.png", );
if( !object.data )
{
std::cout<< "Error reading object " << std::endl;
return -1;
}
//Detect the keypoints using SURF Detector
int minHessian = 500;
SurfFeatureDetector detector( minHessian );
std::vector<KeyPoint> kp_object;
detector.detect( object, kp_object );
//Calculate descriptors (feature vectors)
SurfDescriptorExtractor extractor;
Mat des_object;
extractor.compute( object, kp_object, des_object );
FlannBasedMatcher matcher;
namedWindow("Good Matches");
namedWindow("Tracking");
std::vector<Point2f> obj_corners(4);
//Get the corners from the object
obj_corners[0] = cvPoint(0,0);
obj_corners[1] = cvPoint( object.cols, 0 );
obj_corners[2] = cvPoint( object.cols, object.rows );
obj_corners[3] = cvPoint( 0, object.rows );
char key = 'a';
int framecount = 0;
VideoCapture cap("booksvideo.avi");
for(; ;)
{
Mat frame;
cap >> frame;
imshow("Good Matches", frame);
Mat des_image, img_matches;
std::vector<KeyPoint> kp_image;
std::vector<vector<DMatch > > matches;
std::vector<DMatch > good_matches;
std::vector<Point2f> obj;
std::vector<Point2f> scene;
std::vector<Point2f> scene_corners(4);
Mat H;
Mat image;
//cvtColor(frame, image, CV_RGB2GRAY);
detector.detect( image, kp_image );
extractor.compute( image, kp_image, des_image );
matcher.knnMatch(des_object, des_image, matches, 2);
for(int i = 0; i < min(des_image.rows-1,(int) matches.size()); i++) //THIS LOOP IS SENSITIVE TO SEGFAULTS
{
if((matches[i][0].distance < 0.6*(matches[i][1].distance)) && ((int) matches[i].size()<=2 && (int) matches[i].size()>0))
{
good_matches.push_back(matches[i][0]);
}
}
//Draw only "good" matches
drawMatches( object, kp_object, image, kp_image, good_matches, img_matches, Scalar::all(-1), Scalar::all(-1), vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS );
if (good_matches.size() >= 4)
{
for( int i = 0; i < good_matches.size(); i++ )
{
//Get the keypoints from the good matches
obj.push_back( kp_object[ good_matches[i].queryIdx ].pt );
scene.push_back( kp_image[ good_matches[i].trainIdx ].pt );
}
H = findHomography( obj, scene, CV_RANSAC );
perspectiveTransform( obj_corners, scene_corners, H);
//Draw lines between the corners (the mapped object in the scene image )
line( img_matches, scene_corners[0] + Point2f( object.cols, 0), scene_corners[1] + Point2f( object.cols, 0), Scalar(0, 255, 0), 4 );
line( img_matches, scene_corners[1] + Point2f( object.cols, 0), scene_corners[2] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[2] + Point2f( object.cols, 0), scene_corners[3] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[3] + Point2f( object.cols, 0), scene_corners[0] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 );
mat_dest_image=cvCloneImage(&(IplImage)image);
mat_frame=cvCloneImage(&(IplImage)frame);
Kalman_Color_Object_Track( ); // The tracking method
}
//Show detected matches
imshow( "Good Matches", img_matches );
for( int i = 0; i < good_matches.size(); i++ )
{ printf( "-- Good Match [%d] Keypoint 1: %d -- Keypoint 2: %d \n", i, good_matches[i].queryIdx, good_matches[i].trainIdx ); }
waitKey(0);
}
return 0;
}

Answer 1

This paper implemented the SIFT descriptor on color images by computing gradient histograms for each channel independently. Perhaps you could try the same approach for SURF features.