potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 15:53:03 +04:00
Code Packages Releases Wiki Activity

Merge pull request #29073 from abhishek-gola:disk_feature_extractor

Browse Source 
Added DISK feature extractor support #29073

closes: https://github.com/opencv/opencv/issues/27083
Merge with: https://github.com/opencv/opencv_extra/pull/1368/

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Abhishek Gola
2026-06-03 15:41:11 +05:30
committed by GitHub
parent a0a660fcb1
commit b0b77e7b32
15 changed files with 793 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/features/include/opencv2/features.hpp
+79
View File
@@ -669,9 +669,88 @@ public:
CV_WRAP virtual void setK(double k) = 0;
CV_WRAP virtual double getK() const = 0;
CV_WRAP virtual String getDefaultName() const CV_OVERRIDE;
};
#if defined(HAVE_OPENCV_DNN) || defined(CV_DOXYGEN)
/** @brief DISK feature detector and descriptor, based on a DNN model.
DISK (Deep Image Structure and Keypoints) is a learned local-feature pipeline that produces
keypoints and 128-D L2-normalized descriptors via a single forward pass through a fully
convolutional network. This class wraps an ONNX export of the pre-trained DISK model through
cv::dnn::Net and exposes it under the standard cv::Feature2D interface so it can be used as
a drop-in alternative to SIFT/ORB.
The class assumes the ONNX model has a single input named `image` taking an N×3×H×W float32
tensor in [0, 1] (RGB channel order) and three outputs named `keypoints` (N×2), `scores` (N)
and `descriptors` (N×128).
*/
class CV_EXPORTS_W DISK : public Feature2D
{
public:
/** @brief Creates a DISK detector.
@param modelPath Path to the DISK ONNX model.
@param maxKeypoints Maximum number of keypoints to return per image. The strongest
responses (by network score) are kept; -1 keeps all detections.
@param scoreThreshold Discard keypoints with network score strictly below this value.
@param imageSize Target input size (width, height) fed to the network. Use Size()
(the default) to fall back to the network's expected fixed input
shape of 1024x1024. When overriding, both dimensions must be
positive multiples of 16, since DISK downsamples by a factor of 16.
@param backendId DNN backend identifier (see cv::dnn::Backend); 0 = DNN_BACKEND_DEFAULT.
@param targetId DNN target identifier (see cv::dnn::Target); 0 = DNN_TARGET_CPU.
*/
CV_WRAP static Ptr<DISK> create(const String& modelPath,
int maxKeypoints = -1,
float scoreThreshold = 0.0f,
const Size& imageSize = Size(),
int backendId = 0,
int targetId = 0);
/** @brief Creates a DISK detector from an in-memory model buffer.
This overload loads the DISK ONNX model from a buffer instead of a file on disk. It is
intended for cases where the model is read from application resources (for example Android
assets) and is not available as a path on the filesystem.
@param bufferModel A buffer containing the contents of the DISK ONNX model.
@param maxKeypoints Maximum number of keypoints to return per image. The strongest
responses (by network score) are kept; -1 keeps all detections.
@param scoreThreshold Discard keypoints with network score strictly below this value.
@param imageSize Target input size (width, height) fed to the network. Use Size()
(the default) to fall back to the network's expected fixed input
shape of 1024x1024. When overriding, both dimensions must be
positive multiples of 16, since DISK downsamples by a factor of 16.
@param backendId DNN backend identifier (see cv::dnn::Backend); 0 = DNN_BACKEND_DEFAULT.
@param targetId DNN target identifier (see cv::dnn::Target); 0 = DNN_TARGET_CPU.
@note In C++ this is an overload of @ref create. The Python/Java/Objective-C bindings expose
it as `createFromMemory`, because Objective-C selectors are not disambiguated by argument
type and would otherwise clash with the file-path @ref create.
*/
CV_WRAP_AS(createFromMemory) static Ptr<DISK> create(const std::vector<uchar>& bufferModel,
int maxKeypoints = -1,
float scoreThreshold = 0.0f,
const Size& imageSize = Size(),
int backendId = 0,
int targetId = 0);
CV_WRAP virtual void setMaxKeypoints(int maxKeypoints) = 0;
CV_WRAP virtual int getMaxKeypoints() const = 0;
CV_WRAP virtual void setScoreThreshold(float threshold) = 0;
CV_WRAP virtual float getScoreThreshold() const = 0;
CV_WRAP virtual void setImageSize(const Size& size) = 0;
CV_WRAP virtual Size getImageSize() const = 0;
CV_WRAP virtual String getDefaultName() const CV_OVERRIDE;
};
#endif // HAVE_OPENCV_DNN || CV_DOXYGEN
/** @brief Class for extracting blobs from an image. :
The class implements a simple algorithm for extracting blobs from an image: