Revision history [back]

NOVICE question: http://docs.opencv.org/3.0-beta/modules/features2d/doc/feature_detection_and_description.html states that AKAZE descriptors can only be used with KAZE or AKAZE keypoints. Try to avoid using extract and detect instead of operator() due to performance reasons.

so I tried to use KAZE detector with AKAZE descriptor extractor:

Ptr<feature2d> detector = cv::KAZE::create(); Ptr<descriptorextractor> extractor = cv::AKAZE::create(); ... vector<keypoint> keypoint; Mat features; detector->detect(img, keypoint);

extractor->compute(img, keypoint, features); //<- error at this line

generate the following error: OpenCV Error: Assertion failed (0 <= kpts[i].class_id && kpts[i].class_id < static_cast<int>(evolution_.size())) in cv::AKAZEFeatures::Compute_Descriptors, file ......\src\opencv\modules\features2d\src\kaze\AKAZEFeatures.cpp, line 712

However, when both detector and extractor are the same, there is no problem. Any help is appreciated, thanks. JC

NOVICE question: http://docs.opencv.org/3.0-beta/modules/features2d/doc/feature_detection_and_description.html states that AKAZE descriptors can only be used with KAZE or AKAZE keypoints. Try to avoid using extract and detect instead of operator() due to performance reasons.

so I tried to use KAZE detector with AKAZE descriptor extractor:

Ptr<Feature2D> detector = cv::KAZE::create();
Ptr<descriptorextractor> Ptr<DescriptorExtractor> extractor = cv::AKAZE::create();
 ...
vector<keypoint> vector<KeyPoint> keypoint;
Mat features;
detector->detect(img, keypoint);
 
keypoint);
extractor->compute(img, keypoint, features);  //<- error at this lineline

OpenCV Error: Assertion failed (0 <= kpts[i].class_id && kpts[i].class_id < static_cast<int>(evolution_.size())) 
in cv::AKAZEFeatures::Compute_Descriptors, file ......\src\opencv\modules\features2d\src\kaze\AKAZEFeatures.cpp, ..\..\..\src\opencv\modules\features2d\src\kaze\AKAZEFeatures.cpp, line 712
712