Tomoaki Teshima
63f5f93063
fix test failure on ODROID-N2
2020-04-28 21:46:31 +09:00
mshabunin
3e28d51779
Fixed several OpenCL compiler warnings
2016-11-07 16:49:12 +03:00
Vadim Pisarevsky
5a94a95fbf
improvements in Haar CascadeClassifier: 1) use CV_32S instead of CV_32F for the integral of squares (which is more accurate and more efficient); 2) skip the window if its contrast is too low
2015-05-28 19:33:21 +03:00
Yan Wang
433c3da7cf
Optimize the performance of cascade OpenCL kernel.
...
1. Use built-in mad() instead of += and *.
2. For stump stages, if weight.z == 0, avoid unnecessary calculation
because some features only have 2 rectangles..
It could improve
OCL_Cascade_Image_MinSize_CascadeClassifier.CascadeClassifier/*
about 10% mean values.
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2015-03-23 17:47:40 +08:00
Yan Wang
99aaf4030a
Remove unnecessary barrier in runHaarClassifier().
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2015-02-02 16:55:11 +08:00
Yan Wang
df697f6520
Optimize runLBPClassifierStumpSimple by built-in mad24.
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2015-01-22 16:36:16 +08:00
Yan Wang
f5b21e8141
Avoid deadlock becasue some work item couldn't reach barrier in loop
...
and unsynchronized.
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2015-01-20 13:45:33 +08:00
Yan Wang
07ab0c1c53
Avoid compile unnecessary OpenCL kernel.
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2015-01-14 19:52:41 +08:00
Yan Wang
9699fde8d2
Use hypot to do vector calculation.
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2014-12-30 14:12:28 +08:00
Yan Wang
efa84d8225
Use preprocessor for constant values in OpenCL kernel instead of
...
the parameter variable.
It could improve the performance of
OCL_Cascade_Image_MinSize_CascadeClassifier.CascadeClassifier/*.
Especially,
OCL_Cascade_Image_MinSize_CascadeClassifier.CascadeClassifier/15
OCL_Cascade_Image_MinSize_CascadeClassifier.CascadeClassifier/16
could be improved about 2% in Intel platform.
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
2014-12-16 16:21:05 +08:00
Alexander Karsakov
b14c314fc3
Fixed incorrect thread synchronizations
2014-03-20 13:03:03 +04:00
Alexander Karsakov
30a8308f8e
Enabled Intel-specific optimizations for HOG detector.
2014-03-19 17:30:13 +04:00
Alexander Karsakov
4698d62125
Removed workaround for Intel platform.
2014-03-14 14:18:52 +04:00
Andrey Pavlenko
22146e4b18
Merge pull request #2234 from KonstantinMatskevich:ocl_tapi_hog
2014-02-04 16:35:12 +04:00
Vadim Pisarevsky
de4b1c668d
hopefully fixed compile warnings and the doc builder warnings
2014-02-03 16:36:36 +04:00
Vadim Pisarevsky
30593ee55e
3rd attempt to prepare patch with improved OpenCL kernels of CascadeClassifier.
2014-02-03 15:12:27 +04:00
Konstantin Matskevich
9a62df1650
HOG
2014-02-03 14:46:52 +04:00
Vadim Pisarevsky
8998186ce4
removed extra whitespaces and hopefully fixed the test failures
2013-12-23 18:41:54 +04:00
Vadim Pisarevsky
d084d19779
added OpenCL optimization for LBP-based face detector
2013-12-23 15:28:50 +04:00
Vadim Pisarevsky
1540910542
started adding OpenCL acceleration of LBP-based object detectors
2013-12-20 18:39:35 +04:00
Vadim Pisarevsky
f41f633d2d
fixed various warnings from the “doc” and other builders
2013-12-19 16:31:30 +04:00
Vadim Pisarevsky
ec3f22cee2
renamed OpenCL kernel filename; made some final changes
2013-12-19 14:29:28 +04:00
Vadim Pisarevsky
b7553d4e2e
some attempts to tune the performance
2013-12-19 14:09:44 +04:00
Vadim Pisarevsky
02fb3f0a77
it finally works!!!
2013-12-17 20:55:49 +04:00
Vadim Pisarevsky
302a5adcc2
converted Haar cascades to the new format; now they are handled with C++ code.
2013-12-10 22:54:37 +04:00
