e0f8bb83a6
Merge pull request #14994 from terfendail:wintr_undistort
...
WUI based implementation to initUndistortRectifyMap (#14994 )
* Add initUndistortRectifyMap performance test
* Move cv namespace boundaries
* Add wide universal intrinsics based implementation to initUndistortRectifyMap
* Dispatch undistort
5 years ago
c9fcc12e3b
Merge pull request #15048 from ChipKerchner:reduceStoreGatheringThreshold
...
* Reduce store gathering pressures - speeds thresholds by up to 20%
* Rename temporary histogram array and initialize so that MACOSX builder is happy
5 years ago
894ad33bf4
Fix pixel value evaluation overflow in bit-exact GaussianBlur implementation
5 years ago
32c6e58bdb
imgproc: fix unaligned memory access
...
may cause crashes on ARM platform
5 years ago
594a95839c
fix test failure of OCL_ImgProc/CvtColor8u.mRGBA2RGBA
5 years ago
82e5b961d3
Fixed initUndistortRectifyMap AVX2 implementation
5 years ago
a37201abee
Fix crash, add assert and test
5 years ago
9befb7a1d7
Merge pull request #14916 from terfendail:wsignmask_deprecated
...
* Avoid using v_signmask universal intrinsic and mark it as deprecated
* Renamed v_find_negative to v_scan_forward
5 years ago
3e4a195b61
Merge pull request #14936 from StefanBruens:crosscorr_cleanup
...
Crosscorr cleanup (#14936 )
* Simplify code for convolution destination type/size
For the 2d filter code, destination size equals source size, and the
crossCorr function even (re-)creates the output matrix with the given size.
The number of channels also have to match. The destination type() is the
one used to create the output matrix, so we can use its type() here.
This is a preparatory patch.
Signed-off-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>
* Remove redundant destination size and type parameters from crossCorr
All calling sites of crossCorr already use (...,
mat, mat.size(), mat.type(), ...), so the parameters are redundant.
Signed-off-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>
5 years ago
4a6888ccf6
imgproc: fix kmeans() call from grabCut()
6 years ago
5ac55fc132
core: eliminate AVX512 build warnings
...
from MSVS2017 and GCC8 -O1 mode
6 years ago
549c53121a
fix the bug, when k[4] is negative, icdist may be negative at the edge of image.
6 years ago
d2aadabc5e
Merge pull request #14743 from terfendail:wui512_fixvswarn
...
Fix for MSVS2019 build warnings (#14743 )
* AVX512 arch support for MSVS
* Fix for MSVS2019 build warnings: updated integral() AVX512 implementation
* Fix for MSVS2019 build warnings: reworked v_rotate_right AVX512 implementation
* fix indentation
6 years ago
1e9ad5476d
core(intrin): drop hasSIMD128 checks
...
- use compile-time checks instead (`#if CV_SIMD128`)
- runtime checks are useless
6 years ago
a38157a1f4
Fix https://github.com/opencv/opencv/issues/14265
6 years ago
3b015dfc7d
Merge pull request #14210 from terfendail:wui_512
...
AVX512 wide universal intrinsics (#14210 )
* Added implementation of 512-bit wide universal intrinsics(WIP)
* Added implementation of 512-bit wide universal intrinsics: implemented WUI vector types(WIP)
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load/store
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented fp16 load/store
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented recombine and zip, implemented non-saturating and saturating arithmetics
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented bit operations
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented comparisons
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented lane shifts and reduction
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented absolute values
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented rounding and cast to float
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented LUT
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented type extension/narrowing and matrix operations
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load_deinterleave for 2 and 3 channels images
* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented load_deinterleave for 2- and implemented for 4-channel images
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented store_interleave
* Added implementation of 512-bit wide universal intrinsics(WIP): implemented signmask and checks
* Added implementation of 512-bit wide universal intrinsics(WIP): build fixes
* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented popcount in case AVX512_BITALG is unavailable
* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented zip
* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented rotate for s8 and s16
* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented interleave/deinterleave for s8 and s16
* Added implementation of 512-bit wide universal intrinsics(WIP): updated v512_set macros
* Added implementation of 512-bit wide universal intrinsics(WIP): fix for GCC wrong _mm512_abs_pd definition
* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_zip to avoid AVX512_VBMI intrinsics
* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_invsqrt to avoid AVX512_ER intrinsics
* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_rotate, v_popcount and interleave/deinterleave for U8 to avoid AVX512_VBMI intrinsics
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed integral image SIMD part
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed warnings
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed load_deinterleave for u8 and u16
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed v_invsqrt accuracy for f64
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave/deinterleave for u32 and u64
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave_pairs, interleave_quads and pack_triplets
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left/right, part 2
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed 512-wide universal intrinsics based resize
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed findContours by avoiding use of uint64 dependent 512-wide v_signmask()
* Added implementation of 512-bit wide universal intrinsics(WIP): fixed trailing whitespaces
* Added implementation of 512-bit wide universal intrinsics(WIP): reworked specific intrinsic sets dependent parts to check availability of intrinsics based on CPU feature group defines
* Added implementation of 512-bit wide universal intrinsics(WIP):Updated AVX512 implementation of v_popcount to avoid AVX512VPOPCNTDQ intrinsics if unavailable.
* Added implementation of 512-bit wide universal intrinsics(WIP): Fixed universal intrinsics data initialisation, v_mul_wrap, v_floor, v_ceil and v_signmask.
* Added implementation of 512-bit wide universal intrinsics(WIP): Removed hasSIMD512()
* Added implementation of 512-bit wide universal intrinsics(WIP): Fixes for gcc build
* Added implementation of 512-bit wide universal intrinsics(WIP): Reworked v_signmask, v_check_any() and v_check_all() implementation.
6 years ago
8c698262ea
rgb2hls_b: out of bounds read fixed
6 years ago
791ebd05fc
out of bounds read fixed in rgb2luv_b
6 years ago
e07ffe902e
Merge pull request #14616 from savuor:hsv_wide
...
HSV and HLS color conversions rewritten to wide intrinsics (#14616 )
* RGB2HSV_b vectorized
* RGB2HSV_f: widen
* RGB2HSV_f: shorten, more intuitive
* HSV2RGB_f and HSV2RGB_b widen
* hls2rgb_f widen
* instrumentation instead vx_cleanup
* RGB2HLS_f widen
* RGB2HLS_b rewritten to wide universal intrinsics
* define guard against no SIMD code
* hls2rgb_b rewritten
* extra define removed
* warning fixed
* hls2rgb_b: performance fixed
6 years ago
f3319f6140
java: remove redundant declaration of java.lang package
6 years ago
7ed858e38e
Fix issue with solvePnPRansac and Nx3 1-channel input when the number of points is 5. Try to uniform the input shape of projectPoints and undistortPoints.
6 years ago
e90e0ef9aa
Merge pull request #14106 from savuor:lab_wide
...
Lab, Luv and XYZ conversions rewritten to wide intrinsics (#14106 )
* rgb2xyz<float> re-vectorized
* rgb2xyz_i vectorized for ushort and uchar
* xyz2rgb<float> vectorized
* xyz2rgb_i vectorized for both uchar and ushort
* intermediate conversions (int->float) rewritten
* packed rgb2luv rewritten
* (some) float conversions rewritten
* burnt volatile int _3 and similar
* RGB2Lab_b rewritten
* tests: logging made better
* RGB2Lab_f (LRGB path) rewritten
* Lab2RGBfloat rewritten
* Lab2RGBinteger and Lab2RGB_b rewritten to wide universal intrinsics
* Luv2RGBinteger wide vectorized
* RGB2Lab_b fixed: v_sub_wrap instead of saturated sub
* warnings fixed
* trying to fix compilation on older compilers
* using 16x8 registers for 8-element dot product
* cleanup added
* splineInterpolate: loop unrolled, perf fix for f32x4
* Lab2RGBfloat: grab 2x more data to process on f32x4
* nrepeats for Luv2RGBfloat, +20% perf
* minor
* nrepeats to RGB2Lab_f
* Lab2RGBinteger: no tab for linear BGR
* nrepeats for RGB2Luvfloat
* Luv2RGBinteger: no tab for linear RGB
* +10% more to perf of Luv2RGBfloat
* nrepeats for 256-simd for Lab2RGBfloat
* less warnings
* BOM removed
* CV_SIMD_WIDTH used for lanes number checking
* trilinearPackedInterpolate: 128-bit specialization added
* fix build; no vx_cleanup(), instrumentation instead
6 years ago
1aff378ae8
imgproc: fixed bug from intersectConvexConvex
...
Added checks for all of vertices from each contour instead of checking
only for the first vertex.
6 years ago
1c180f4c7f
imgproc: fix RemoveOverlaps() with empty input vector
6 years ago
3f9343e238
Update imgproc.hpp
6 years ago
0fe17eeb68
Implementing AVX512 Support for 1 channel mats for CV_64F format
6 years ago
8c8715c4dd
fix static analysis issues
6 years ago
f73b4f4a26
imgproc: revert #13843
...
This reverts commit 00e8c7810f
6 years ago
e0b664f390
fix dftFilter2D
6 years ago
2c07c6718f
imgproc: dispatch morph
6 years ago
5a01227aa1
imgproc: dispatch box_filter
6 years ago
ce3c92eb1f
imgproc: dispatch bilateral_filter
6 years ago
b99c9145bf
imgproc: dispatch smooth
6 years ago
6ec08f268f
imgproc: dispatch medianBlur
6 years ago
8546ac3ce6
imgproc: get rid of filter.avx2.cpp
6 years ago
9a8dbfd57f
imgproc: dispatch filter.cpp
6 years ago
9dc7554089
imgproc: copy .dispatch.cpp
6 years ago
6eac8f78b9
imgproc: copy .simd.hpp
6 years ago
8b541e450b
imgproc: dispatch color*
...
Lab/XYZ modes have been postponed (color_lab.cpp):
- need to split code for tables initialization and for pixels processing first
- no significant performance improvements for switching between SSE42 / AVX2 code generation
6 years ago
f26912960f
imgproc: clone color*.dispatch.cpp
6 years ago
db588bb831
imgproc: clone color*.simd.hpp
6 years ago
d5a2fe5180
perf: ignore _ovx tests
6 years ago
99b39aa5bd
Fixed out of bound reading in LINEAR_EXACT resize for 8UC3
6 years ago
3d1dbd2ccd
clean up C API
6 years ago
3ba49ccecc
imgproc: removed LSD code due original code license conflict
6 years ago
9548093b46
Horizontal line processing for pyrDown() reworked using wide universal intrinsics.
6 years ago
334c4d62b5
Merge pull request #13781 from terfendail:warp_wintr
...
Resize reworked using wide universal intrinsics (#13781 )
* Added wide universal intrinsics optimized implementation for 3 channel bit-exact linear resize
* Reworked linear resize using new wide LUT intrinsics
* Fix for VSX intrinsics
6 years ago
507f8add1c
Implementing AVX512 Support for 2 and 4 channel mats for CV_64F format
6 years ago
00e8c7810f
LineIterator witout a Mat ( #13843 )
...
* LineIterator witout a Mat
cv::LineIterator can be used without being attached to any cv::Mat, it only needs the size and type of data. An alternative constructor has been defined for that.
In that case, a LineIterator can no more be dereferenced with the * operator, but pos() still returns valid pixel positions.
It can be useful when LineIterator is just used to compute positions of pixels on a line, without requiring to build a Mat just for that.
Use case : with a dataset that would represent a huge image, pixel positions can be pre-computed before querying the dataset API.
* Update imgproc.hpp
removed trailing spaces
* Update drawing.cpp
fixed warning
6 years ago
4e679e1cc5
disabled 16u and 32f perf tests
6 years ago
Vitaly Tuzov
Chip Kerchner
Vitaly Tuzov
Alexander Alekhin
Tomoaki Teshima
arnaudbrejeon
StefanBruens
Alexander Alekhin
Kang
bommo1
Rostislav Vasilikhin
Ahmed Ashour
catree
Thang Tran
Suleyman TURKMEN
Brad Kelly
take1014
Pierre Chatelier