Databases
StackOverflow2013
Postsdbo
PODrawing rectangle around detected object using SURF
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PODrawing rectangle around detected object using SURF
    primarykey
    data
    text
    <p>I am trying to detect an object from the following code involving surf detector, I do not want to draw matches, I want to draw a rectangle around the detected object, but somehow I am unable to get correct Homography, please can anyone point out where I am going wrong.</p> <pre><code>#include &lt;stdio.h&gt; #include &lt;iostream&gt; #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; int main() { Mat object = imread( "sample.jpeg", CV_LOAD_IMAGE_GRAYSCALE ); if( !object.data ) { std::cout&lt;&lt; "Error reading object " &lt;&lt; std::endl; return -1; } //Detect the keypoints using SURF Detector int minHessian = 500; SurfFeatureDetector detector( minHessian ); std::vector&lt;KeyPoint&gt; 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; VideoCapture cap(0); namedWindow("Good Matches",0); cvResizeWindow("Good Matches",800,800); std::vector&lt;Point2f&gt; 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; while (key != 27) { Mat frame; cap &gt;&gt; frame; if (framecount &lt; 5) { framecount++; continue; } Mat des_image, img_matches; std::vector&lt;KeyPoint&gt; kp_image; std::vector&lt;vector&lt;DMatch &gt; &gt; matches; std::vector&lt;DMatch &gt; good_matches; std::vector&lt;Point2f&gt; obj; std::vector&lt;Point2f&gt; scene; std::vector&lt;Point2f&gt; 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 &lt; min(des_image.rows-1,(int) matches.size()); i++) //THIS LOOP IS SENSITIVE TO SEGFAULTS { if((matches[i][0].distance &lt; 0.6*(matches[i][1].distance)) &amp;&amp; ((int) matches[i].size()&lt;=2 &amp;&amp; (int) matches[i].size()&gt;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&lt;char&gt;(),DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS); if (good_matches.size() &gt;= 4) { for( int i = 0; i &lt; 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( image, scene_corners[0] + Point2f( object.cols, 0), scene_corners[1] + Point2f( object.cols, 0), Scalar(0, 255, 0), 4 ); line( image, scene_corners[1] + Point2f( object.cols, 0), scene_corners[2] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 ); line( image, scene_corners[2] + Point2f( object.cols, 0), scene_corners[3] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 ); line( image, scene_corners[3] + Point2f( object.cols, 0), scene_corners[0] + Point2f( object.cols, 0), Scalar( 0, 255, 0), 4 ); } //Show detected matches imshow( "Good Matches", image ); key = waitKey(1); } return 0; } </code></pre>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. This table or related slice is empty.
    1. USsum2000
    plurals
    1. This table or related slice is empty.
    1. PL
      singulars
      1. LTLinked
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    1. VO
      singulars
      1. PODrawing rectangle around detected object using SURF
      1. USsum2000
      1. VTFavorite
    2. VO
      singulars
      1. PODrawing rectangle around detected object using SURF
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. PODrawing rectangle around detected object using SURF
      1. This table or related slice is empty.
      1. VTUpMod
    1. COsomehow unable in what way? are you not getting enough good matches, is the calculated homography just plain wrong? maybe you have some matches outside the objects?
      singulars
      1. PODrawing rectangle around detected object using SURF
      1. USpenelope
    2. CO@penelope the matches are good enough, but the rectangle which is supposed to be around the object is not around it, so i guess i am calculating wrong coordinates.
      singulars
      1. PODrawing rectangle around detected object using SURF
      1. USsum2000
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload