Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    text
    copied!<p>Template matching with <code>matchTemplate</code> is not good when your object is rotated or scaled in scene.</p> <p>You should try openCV function from <code>Features2D</code> Framework. For example <code>SIFT</code> or <code>SURF</code> descriptors, and <code>FLANN</code> matcher. Also, you will need <code>findHomography</code> method.</p> <p><a href="http://docs.opencv.org/doc/tutorials/features2d/feature_homography/feature_homography.html#feature-homography">Here</a> is a good example of finding rotated object in scene.</p> <p><strong>Update:</strong></p> <p>In short, algorithm is this:</p> <ol> <li><p>Finding keypoints of your object image 1.1. Extracting descriptors from those keypoints</p></li> <li><p>Finding keypoints of your scene image 2.1 Extracting descriptors from keypoints</p></li> <li><p>Match descriptors by matcher</p></li> <li><p>Analyze your matches</p></li> </ol> <p>There are different classes of FeatureDetectors, DescriptorExtractors, and DescriptorMatches, you may read about them and choose those, that fit good for your tasks.</p> <ul> <li><a href="http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_feature_detectors.html#featuredetector">openCV FeatureDetector</a> (steps 1 and 2 in algorithm above)</li> <li><a href="http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_descriptor_extractors.html#descriptorextractor">openCV DescriptorExtractor</a> ( steps 1.1 and 2.1 in algorithm above ) </li> <li><a href="http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_descriptor_matchers.html#descriptormatcher">openCV DescriptorMatcher</a> ( step 3 in algorithm above )</li> </ul>
 

Querying!

 
Guidance

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