opencv/opencv_contrib
1
0
Fork 0
mirror of https://github.com/opencv/opencv_contrib.git synced 2025-10-19 02:16:34 +08:00
Code Issues Releases Wiki Activity

KCF speedup (#1374)

Browse Source 
* kcf use float data type rather than double.

In our practice, float is good enough and could get better performance.
With this patch, one of my benchmark could get about 20% performance gain.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>

* Offload transpose matrix multiplication to ocl.

The matrix multiplication in updateProjectMatrix is one of the
hotspot. And because of the matrix shape is special, say the
m is very short but the n is very large. The GEMM implementation
in neither the clBLAS nor the in trunk implementation are very
inefficient, I implement an standalone transpose matrix mulplication
kernel here. It can get about 10% performance gain on Intel
desktop platform or 20% performance gain on a braswell platform.
And in the mean time, the CPU utilization will be lower.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>

* Add verification code for kcf ocl transpose mm kernel.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>

* tracking: show FPS in traker sample

* tracking: fix MSVC warnings in KCF

* tracking: move OCL kernel initialization to constructor in KCF
This commit is contained in:
Vladislav Sovrasov
2017-10-10 13:54:22 +03:00
committed by Vadim Pisarevsky
parent 0058eca130
commit 41995b76e8
7 changed files with 32993 additions and 32837 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
modules/tracking/samples/tracker.cpp
View File

@@ -117,6 +117,7 @@ int main( int argc, char** argv ){
bool initialized = false;
int frameCounter = 0;
int64 timeTotal = 0;
for ( ;; )
{
@@ -142,11 +143,14 @@ int main( int argc, char** argv ){
}
else if( initialized )
{
int64 frameTime = getTickCount();
//updates the tracker
if( tracker->update( frame, boundingBox ) )
{
rectangle( image, boundingBox, Scalar( 255, 0, 0 ), 2, 1 );
}
frameTime = getTickCount() - frameTime;
timeTotal += frameTime;
}
imshow( "Tracking API", image );
frameCounter++;
@@ -159,5 +163,8 @@ int main( int argc, char** argv ){
paused = !paused;
}
double s = frameCounter / (timeTotal / getTickFrequency());
printf("FPS: %f\n", s);
return 0;
}