Strange error calculation in calcOpticalFlowPyrLK (Bug #1651)

Added by Vladislav Vinogradov about 13 years ago. Updated almost 13 years ago.

Status:Done Start date:2012-03-05
Priority:Normal Due date:
Assignee:Vadim Pisarevsky % Done:

0%
Category:imgproc, video
Target version:2.4.0
Affected version: Operating System:
Difficulty: HW Platform:
Pull request:

Description

The documentation says that output error in calcOpticalFlowPyrLK is calculated as difference between patches around the original and moved points.
In iteration cycle point on the second image is used as center of patch when we compute difference between patches.
But in the end when we compute error, point on the second image is used as left top corner of patch.
Is this right? Or it should be the center of patch?

lkpyramid.cpp.patch (593 Bytes) Vladislav Vinogradov, 2012-03-05 11:58 am

Associated revisions

Revision 855feedd
Added by Vladislav Vinogradov about 13 years ago

fixed error calculation in gpu::PyrLKOpticalFlow (Bug #1651)

Revision 599d51ec
Added by Roman Donchenko over 11 years ago

Merge pull request #1651 from ilya-lavrenov:misprint

History

#1
Updated by Anatoly Baksheev about 13 years ago

Vadim, i guess this question is addressed to you.

  • Assignee set to Vadim Pisarevsky

#2
Updated by Vadim Pisarevsky about 13 years ago

thanks! applied in trunk

  • Status changed from Open to Done

#3
Updated by Andrey Kamaev almost 13 years ago

  • Target version set to 2.4.0

Also available in: Atom PDF