From a6ec12f58b88f8384ecebb87b60153ee4912e3c7 Mon Sep 17 00:00:00 2001
From: Alexander Smorkalov <2536374+asmorkalov@users.noreply.github.com>
Date: Mon, 23 Sep 2024 08:44:22 +0300
Subject: [PATCH] Merge pull request #26163 from asmorkalov:as/HAL_schaar_deriv

HAL interface for Sharr derivatives needed for Lukas-Kanade algorithm #26163

### 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
- [ ] 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
---
 3rdparty/carotene/hal/tegra_hal.hpp   | 16 ++++++++++++++++
 modules/video/src/hal_replacement.hpp | 21 +++++++++++++++++++++
 modules/video/src/lkpyramid.cpp       |  3 +++
 3 files changed, 40 insertions(+)

diff --git a/3rdparty/carotene/hal/tegra_hal.hpp b/3rdparty/carotene/hal/tegra_hal.hpp
index 31182a029a..2e07b7f526 100644
--- a/3rdparty/carotene/hal/tegra_hal.hpp
+++ b/3rdparty/carotene/hal/tegra_hal.hpp
@@ -1962,4 +1962,20 @@ inline int TEGRA_LKOpticalFlowLevel(const uchar *prev_data, size_t prev_data_ste
 #define cv_hal_LKOpticalFlowLevel TEGRA_LKOpticalFlowLevel
 #endif // __ARM_ARCH=7
 
+#if 0 // OpenCV provides fater parallel implementation
+inline int TEGRA_ScharrDeriv(const uchar* src_data, size_t src_step,
+                      short* dst_data, size_t dst_step,
+                      int width, int height, int cn)
+{
+    if (!CAROTENE_NS::isSupportedConfiguration())
+        return CV_HAL_ERROR_NOT_IMPLEMENTED;
+
+    CAROTENE_NS::ScharrDeriv(CAROTENE_NS::Size2D(width, height), cn, src_data, src_step, dst_data, dst_step);
+    return CV_HAL_ERROR_OK;
+}
+
+#undef cv_hal_ScharrDeriv
+#define cv_hal_ScharrDeriv TEGRA_ScharrDeriv
+#endif
+
 #endif
diff --git a/modules/video/src/hal_replacement.hpp b/modules/video/src/hal_replacement.hpp
index 8d10ab39d1..b3551d1d3f 100644
--- a/modules/video/src/hal_replacement.hpp
+++ b/modules/video/src/hal_replacement.hpp
@@ -67,6 +67,27 @@ inline int hal_ni_LKOpticalFlowLevel(const uchar *prev_data, size_t prev_data_st
 #define cv_hal_LKOpticalFlowLevel hal_ni_LKOpticalFlowLevel
 //! @endcond
 
+/**
+@brief Computes Schaar derivatives with inteleaved layout xyxy...
+@param src_data source image data
+@param src_step source image step
+@param dst_data destination buffer data
+@param dst_step destination buffer step
+@param width image width
+@param height image height
+@param cn source image channels
+**/
+inline int hal_ni_ScharrDeriv(const uchar* src_data, size_t src_step,
+                              short* dst_data, size_t dst_step,
+                              int width, int height, int cn)
+{
+    return CV_HAL_ERROR_NOT_IMPLEMENTED;
+}
+
+//! @cond IGNORED
+#define cv_hal_ScharrDeriv hal_ni_ScharrDeriv
+//! @endcond
+
 //! @}
 
 #if defined(__clang__)
diff --git a/modules/video/src/lkpyramid.cpp b/modules/video/src/lkpyramid.cpp
index a9917595e9..1ed0482447 100644
--- a/modules/video/src/lkpyramid.cpp
+++ b/modules/video/src/lkpyramid.cpp
@@ -63,6 +63,9 @@ static void calcScharrDeriv(const cv::Mat& src, cv::Mat& dst)
     int rows = src.rows, cols = src.cols, cn = src.channels(), depth = src.depth();
     CV_Assert(depth == CV_8U);
     dst.create(rows, cols, CV_MAKETYPE(DataType<deriv_type>::depth, cn*2));
+
+    CALL_HAL(ScharrDeriv, cv_hal_ScharrDeriv, src.data, src.step, (short*)dst.data, dst.step, cols, rows, cn);
+
     parallel_for_(Range(0, rows), cv::detail::ScharrDerivInvoker(src, dst), cv::getNumThreads());
 }