Abstract
|
<p>We investigate the estimation of … <p>We investigate the estimation of illuminance flow using Histograms of Oriented Gradient features (HOGs). In a regression setting, we found for both ridge regression and support vector machines, that the optimal solution shows close resemblance to the gradient based structure tensor (also known as the second moment matrix). Theoretical results are presented showing in detail how the structure tensor and the HOGs are connected. This relation will benefit computer vision tasks such as affine invariant texture/object matching using HOGs. Several properties of HOGs are presented, among others, how many bins are required for a directionality measure, and how to estimate HOGs through spatial averaging that requires no binning.</p>raging that requires no binning.</p>
|
Author
|
Stefan Karlsson +
, Sylvia C. Pont +
, Jan J. Koenderink +
, Andrew Zisserman +
|
DOI
|
http://dx.doi.org/10.1007/s11263-010-0353-7 +
|
Diva
|
http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:537591
|
EndPage
|
312 +
|
Issue
|
3 +
|
Journal
|
International Journal of Computer Vision +
|
PublicationType
|
Journal Paper +
|
Publisher
|
Elsevier +
|
StartPage
|
304 +
|
Title
|
Illuminance Flow Estimation by Regression +
|
Volume
|
90 +
|
Year
|
2010 +
|
Has queryThis property is a special property in this wiki.
|
Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
, Publications:Illuminance Flow Estimation by Regression +
|
Categories |
Publication +
|
Modification dateThis property is a special property in this wiki.
|
30 September 2016 20:40:17 +
|