Backport to 4.x: patchNaNs() SIMD acceleration #24480
backport from #23098
connected PR in extra: [#1118@extra](https://github.com/opencv/opencv_extra/pull/1118)
### This PR contains:
* new SIMD code for `patchNaNs()`
* CPU perf test
<details>
<summary>Performance comparison</summary>
Geometric mean (ms)
|Name of Test|noopt|sse2|avx2|sse2 vs noopt (x-factor)|avx2 vs noopt (x-factor)|
|---|:-:|:-:|:-:|:-:|:-:|
|PatchNaNs::OCL_PatchNaNsFixture::(640x480, 32FC1)|0.019|0.017|0.018|1.11|1.07|
|PatchNaNs::OCL_PatchNaNsFixture::(640x480, 32FC4)|0.037|0.037|0.033|1.00|1.10|
|PatchNaNs::OCL_PatchNaNsFixture::(1280x720, 32FC1)|0.032|0.032|0.033|0.99|0.98|
|PatchNaNs::OCL_PatchNaNsFixture::(1280x720, 32FC4)|0.072|0.072|0.070|1.00|1.03|
|PatchNaNs::OCL_PatchNaNsFixture::(1920x1080, 32FC1)|0.051|0.051|0.050|1.00|1.01|
|PatchNaNs::OCL_PatchNaNsFixture::(1920x1080, 32FC4)|0.137|0.138|0.128|0.99|1.06|
|PatchNaNs::OCL_PatchNaNsFixture::(3840x2160, 32FC1)|0.137|0.128|0.129|1.07|1.06|
|PatchNaNs::OCL_PatchNaNsFixture::(3840x2160, 32FC4)|0.450|0.450|0.448|1.00|1.01|
|PatchNaNs::PatchNaNsFixture::(640x480, 32FC1)|0.149|0.029|0.020|5.13|7.44|
|PatchNaNs::PatchNaNsFixture::(640x480, 32FC2)|0.304|0.058|0.040|5.25|7.65|
|PatchNaNs::PatchNaNsFixture::(640x480, 32FC3)|0.448|0.086|0.059|5.22|7.55|
|PatchNaNs::PatchNaNsFixture::(640x480, 32FC4)|0.601|0.133|0.083|4.51|7.23|
|PatchNaNs::PatchNaNsFixture::(1280x720, 32FC1)|0.451|0.093|0.060|4.83|7.52|
|PatchNaNs::PatchNaNsFixture::(1280x720, 32FC2)|0.892|0.184|0.126|4.85|7.06|
|PatchNaNs::PatchNaNsFixture::(1280x720, 32FC3)|1.345|0.311|0.230|4.32|5.84|
|PatchNaNs::PatchNaNsFixture::(1280x720, 32FC4)|1.831|0.546|0.436|3.35|4.20|
|PatchNaNs::PatchNaNsFixture::(1920x1080, 32FC1)|1.017|0.250|0.160|4.06|6.35|
|PatchNaNs::PatchNaNsFixture::(1920x1080, 32FC2)|2.077|0.646|0.605|3.21|3.43|
|PatchNaNs::PatchNaNsFixture::(1920x1080, 32FC3)|3.134|1.053|0.961|2.97|3.26|
|PatchNaNs::PatchNaNsFixture::(1920x1080, 32FC4)|4.222|1.436|1.288|2.94|3.28|
|PatchNaNs::PatchNaNsFixture::(3840x2160, 32FC1)|4.225|1.401|1.277|3.01|3.31|
|PatchNaNs::PatchNaNsFixture::(3840x2160, 32FC2)|8.310|2.953|2.635|2.81|3.15|
|PatchNaNs::PatchNaNsFixture::(3840x2160, 32FC3)|12.396|4.455|4.252|2.78|2.92|
|PatchNaNs::PatchNaNsFixture::(3840x2160, 32FC4)|17.174|5.831|5.824|2.95|2.95|
</details>
### 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
dnn: add shared fastNorm kernel for mvn, instance norm and layer norm #24409
Relates https://github.com/opencv/opencv/pull/24378#issuecomment-1756906570
TODO:
- [x] add fastNorm
- [x] refactor layer norm with fastNorm
- [x] refactor mvn with fastNorm
- [ ] add onnx mvn in importer (in a new PR?)
- [ ] refactor instance norm with fastNorm (in another PR https://github.com/opencv/opencv/pull/24378, need to merge this one first though)
### 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
Extend the signature of imdecodemulti() #24405
(Edited after addressing Reviewers' comments.)
Add an argument to `imdecodemulti()` to enable optional selection of pages of multi-page images.
Be default, all pages are decoded. If used, the additional argument may specify a continuous selection of pages to decode.
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [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] I agree to contribute to the project under Apache 2 License.
- [X] The PR is proposed to the proper branch
- [ ] 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
Refactor ObjectiveC Range class #24454
### Pull Request Readiness Checklist
- [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
Fix for build issue in #24405
Video tracking (dnn): set backend and target for TrackerVit #24461Resolves#24460
### 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
videoio: Add raw encoded video stream muxing to cv::VideoWriter with CAP_FFMPEG #24363
Allow raw encoded video streams (e.g. h264[5]) to be encapsulated by `cv::VideoWriter` to video containers (e.g. mp4/mkv).
Operates in a similar way to https://github.com/opencv/opencv/pull/15290 where encapsulation is enabled by setting the `VideoWriterProperties::VIDEOWRITER_PROP_RAW_VIDEO` flag when constructing `cv::VideoWriter` e.g.
```
VideoWriter container(fileNameOut, api, fourcc, fps, { width, height }, { VideoWriterProperties::VIDEOWRITER_PROP_RAW_VIDEO, 1 });
```
and each raw encoded frame is passed as single row of a `CV_8U` `cv::Mat`.
The main reason for this PR is to allow `cudacodec::VideoWriter` to output its encoded streams to a suitable container, see https://github.com/opencv/opencv_contrib/pull/3569.
### 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
Ellipses supported added for Einsum Layer #24322
This PR added addresses issues not covered in #24037. Namely these are:
Test case for this patch is in this PR [#1106](https://github.com/opencv/opencv_extra/pull/1106) in opencv extra
Added:
- [x] Broadcasting reduction "...ii ->...I"
- [x] Add lazy shape deduction. "...ij, ...jk->...ik"
Features to add:
- [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik")
- [ ] Add support for CUDA backend
- [ ] BatchWiseMultiply optimize
- [ ] Performance test
### 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
- [ ] 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
Pertaining Issue: https://github.com/opencv/opencv/issues/5697
### 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
* Optimize some function with lasx.
Optimize some function with lasx. #23929
This patch optimizes some lasx functions and reduces the runtime of opencv_test_core from 662,238ms to 633603ms on the 3A5000 platform.
### 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
dnn: fix HAVE_TIMVX macro definition in dnn test #24425
### 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
Native ONNX to Inference Engine backend #21066Resolves#21052
### 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 other license that is incompatible with OpenCV
- [x] The PR is proposed to proper branch
- [x] There is reference to original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
- [ ] The feature is well documented and sample code can be built with the project CMake
This pointer is called unconditionally in BarcodeImpl::initDecode
assuming the size of the image is outside the specified bounds. This
seems to not cause problems on optimized builds, I assume because the
optimizer sees through the processImageScale call to see that it can be
reduced to a resize call. Leaving it as is relies on undefined
behavior.
This was the least invasive change I could make, however, it might be
worthwhile to pull up the logic for a resize so that a SuperScale does
not need to be allocated, which seems to be the most common case.
Speed up line merging in INTER_AREA #24412
This provides a 10 to 20% speed-up.
Related perf test fix: https://github.com/opencv/opencv/pull/24417
This is a split of https://github.com/opencv/opencv/pull/23525 that will be updated to only deal with column merging.
### 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
Supporting protobuf v22 and later(with abseil-cpp/C++17) #24372
fix https://github.com/opencv/opencv/issues/24369
related https://github.com/opencv/opencv/issues/23791
1. This patch supports external protobuf v22 and later, it required abseil-cpp and c++17.
Even if the built-in protobuf is upgraded to v22 or later,
the dependency on abseil-cpp and the requirement for C++17 will continue.
2. Some test for caffe required patched protobuf, so this patch disable them.
This patch is tested by following libraries.
- Protobuf: /usr/local/lib/libprotobuf.so (4.24.4)
- abseil-cpp: YES (20230125)
### 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
* added more or less cross-platform (based on POSIX signal() semantics) method to detect various NEON extensions, such as FP16 SIMD arithmetics, BF16 SIMD arithmetics, SIMD dotprod etc. It could be propagated to other instruction sets if necessary.
* hopefully fixed compile errors
* continue to fix CI
* another attempt to fix build on Linux aarch64
* * reverted to the original method to detect special arm neon instructions without signal()
* renamed FP16_SIMD & BF16_SIMD to NEON_FP16 and NEON_BF16, respectively
* removed extra whitespaces
GSoC Add ONNX Support for GatherElements #24092
Merge with: https://github.com/opencv/opencv_extra/pull/1082
Adds support to the ONNX operator GatherElements [operator docs](https://github.com/onnx/onnx/blob/main/docs/Operators.md#GatherElements)
Added tests to opencv_extra at pull request https://github.com/opencv/opencv_extra/pull/1082
### 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
Fixed CumSum layer inplace flag #24367
When exclusive is false:
dst[i] = dst[i-1] + src[i]
When exclusive is true:
dst[i] = dst[i-1] + src[i-1]
So CumSum layer can be inplace only when exclusive flag is false.
Encode QR code data to UTF-8 #24350
### Pull Request Readiness Checklist
**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1105
resolves https://github.com/opencv/opencv/issues/23728
This is first PR in a series. Here we just return a raw Unicode. Later I will try expand QR codes decoding methods to use ECI assignment number and return a string with proper encoding, not only UTF-8 or raw unicode.
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
Implement color conversion from RGB to YUV422 family #24333
Related PR for extra: https://github.com/opencv/opencv_extra/pull/1104
Hi,
This patch provides CPU and OpenCL implementations of color conversions from RGB/BGR to YUV422 family (such as UYVY and YUY2).
These features would come in useful for enabling standard RGB images to be supplied as input to algorithms or networks that make use of images in YUV422 format directly (for example, on resource constrained devices working with camera images captured in YUV422).
The code, tests and perf tests are all written following the existing pattern. There is also an example `bin/example_cpp_cvtColor_RGB2YUV422` that loads an image from disk, converts it from BGR to UYVY and then back to BGR, and displays the result as a visual check that the conversion works.
The OpenCL performance for the forward conversion implemented here is the same as the existing backward conversion on my hardware. The CPU implementation, unfortunately, isn't very optimized as I am not yet familiar with the SIMD code.
Please let me know if I need to fix something or can make other modifications.
Thanks!
### 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
- [x] The feature is well documented and sample code can be built with the project CMake
* remove Conformance from test names
* integrate neon optimization into default
* quick fix: define CV_NEON_AARCH64 0 for non NEON platforms
* remove var batch that leads to memory leak
* put neon code back to fast_gemm_kernels.simd
* reorganize code to reduce duplicate code
Add HAL implementation hooks to cv::flip() and cv::rotate() functions from core module #24233
Hello,
This change proposes the addition of HAL hooks for cv::flip() and cv::rotate() functions from OpenCV core module.
Flip and rotation are functions commonly available from 2D hardware accelerators. This is convenient provision to enable custom optimized implementation of image flip/rotation on systems embedding such accelerator.
Thank you
### 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
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Rewrite Universal Intrinsic code: float related part #24325
The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API.
The series of PRs is listed below:
#23885 First patch, an example
#23980 Core module
#24058 ImgProc module, part 1
#24132 ImgProc module, part 2
#24166 ImgProc module, part 3
#24301 Features2d and calib3d module
#24324 Gapi module
This patch (hopefully) is the last one in the series.
This patch mainly involves 3 parts
1. Add some modifications related to float (CV_SIMD_64F)
2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`,
then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD`
3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments
- Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....`
- Some blocks can not be rewrited directly. (Not commented in the source code, just listed here)
- ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct)
- ./modules/imgproc/src/color_lab.cpp (Array of vector type)
- ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type)
- ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`)
These algorithms will need to be redesigned to accommodate scalable backends.
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Fix tests writing to current work dir #24343
Several tests were writing files in the current work directory and did not clean up after test. Moved all temporary files to the `/tmp` dir and added a cleanup code.
Fixed CumSum dnn layer #24353Fixes#20110
The algorithm had several errors, so I rewrote it.
Also the layer didn't work with non constant axis tensor. Fixed it.
Enabled CumSum layer tests from ONNX conformance.
Rostislav Vasilikhin
Liutong HAN
Alexander Smorkalov
Yuantao Feng
Marek Kochanczyk
Giles Payne
Kumataro
cudawarped
Abduragim Shtanchaev
Vincent Rabaud
Amir Hassan
CNClareChen
andrewerf
Vadim Pisarevsky
Aser Atawya
Maksim Shabunin
alexlyulkov
Dmitry Kurtaev
definitelyuncertain
刘佩其
Alex
Sean McBride
jvuillaumier
Wanli
Yuriy Chernyshov
Vadim Levin