ai_mirror
/
opencv
mirror of https://github.com/opencv/opencv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Page: OE 28. Image Stitching
Pages
.clang_format 2018 2019 2020 2021 2022 2023 2024 Archive Branches BuildOpenCV4OpenVINO CI configuration CPU optimizations build options ChangeLog CiteOpenCV Coding_Style_Guide Compact build advice Contributing to G API: PRs Custom OpenCV Android SDK and AAR package build DNN Efficiency Deep Learning in OpenCV Documentation improvement plan Enabling GStreamer source in G API Enabling oneVPL source in G API Evolution Proposals FAQ G API Ideas towards OpenCV 5.0 G API Python Bindings GSoC_2017 GSoC_2018 GSoC_2019 GSoC_2020 GSoC_2021 GSoC_2022 GSoC_2023 GSoC_2024 Graph API Home HowToUsePerfTests HowToWritePerfTests How_to_contribute Huawei CANN Backend Intel OpenVINO backend Linux_contribution_guide MediaSDK encode decode backend OE 0. Template OE 1. Old C API OE 10. FP16 OE 11. Logging OE 12. Lapack OE 13. DNN ONNX Importer OE 14. DNN FP16 OE 15. Bit Exactness OE 16. Mini Halide OE 17. New Filter Engine OE 18. Module Optflow OE 19. Module Stereo OE 2. OpenCV 2 OE 20. Module Calibration OE 21. Module Tracking OE 21. Tracking API OE 22. Module Point Cloud OE 23. Module GAPI OE 24. Module HighGUI OE 25. Fast VideoIO OE 26. Samples OE 27. Wide Universal Intrinsics OE 28. Image Stitching OE 29. Adding AVX512 Support OE 3. OpenCV 3 OE 30. Color Calibration OE 31. Julia Bindings OE 32. Change OpenCV License to Apache 2 OE 33. 3D Module OE 34. Named Parameters OE 35. TFLite support OE 4. OpenCV 4 OE 5. OpenCV 5 OpenCL optimizations OpenCV 5 OpenCV Debugging Facilities OpenCV Platforms OpenCV RISC V OpenCVLogo OpenCV_GSoC OpenCV_GSoC_Application Opencv3 Opencv4 Profiling OpenCV Applications QA_in_OpenCV Running native OpenCV code with Hardware Address Sanitizer TIM VX Backend For Running OpenCV On NPU Template TensorFlow Object Detection API TensorFlow text graphs Using G API with MS ONNX Runtime Using G API with OpenCV AI Kit (OAK) Using G API with OpenVINO Toolkit Using G API with PlaidML backend Video IO hardware acceleration Video capture and write benchmark [Deprecated] Tengine based acceleration
4 OE 28. Image Stitching
Vadim Pisarevsky edited this page 2019-02-21 14:17:52 +03:00
Unescape Escape
Table of Contents
This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Stitching Module

Introduction and Rationale

Stitching module has been around for quite some time and hasn't been refreshed to match changes in rest of the OpenCV.

Stitcher interface is widely used from Python, but lots of features can't be controlled from Python. User experience should be improved.

There is no interoperability with features2d module, all feature finders need to be wrapped manually for stitching module.

Dependencies on legacy CUDA stuff in stitching module let to some compilation problems recently.

Dependencies on xfeatures2d makes it impossible for distributions to provide patent-free stitching module while offering patented algorithms to use with for users that need them.

Proposed solution

  • remove detail::FeaturesFinder and detail::FeaturesMatcher wrapper classes.
  • Use cv::Feature2D and cv::DescriptorMatcher from features2d module.
    • This will allow to use all features and descriptors with stitching modules.
  • Move all estimation code from detail::FeaturesMatcher to detail::Estimator.
    • This also solves problems with dependencies on xfeatures2d.
  • allow user to explicitly set detail::Estimator
  • consolidate creation methods for stitcher.
    • Keep only Stitcher::create,
    • wrap this method for Python.
    • Drop try_use_gpu flag, rely on T-API or user explicitly setting CUDA classes to use.
  • allow users to set FeaturesFinder, DescriptorMatcher, BundleAdjuster etc. from Python
  • drop legacy usage of legacy Levenberg–Marquardt API from bundle adjusters. Replace with new LevMarq API.
  • remove direct usage of CUDA from stitching module (OpenCL alternatives are already available). Move to CUDA modules where it makes sense.

Impact on existing code, compatibility

Changes in Stitcher interface might require some changes in user code. We could introduce some wrapper classes and aliases to ease transition towards using new API with classes from features2d.

Possible alternatives

Keep as is.

References

  1. https://github.com/opencv/opencv/issues?utf8=%E2%9C%93&q=is%3Aissue+label%3A%22category%3A+gpu+%28cuda%29%22+stitching

© Copyright 2024, OpenCV team