Publications:Illuminance Flow Estimation by Regression

From ISLAB/CAISR
Revision as of 13:50, 13 March 2014 by SlawekBot (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title Illuminance Flow Estimation by Regression
Author Stefan Karlsson and Sylvia C. Pont and Jan J. Koenderink and Andrew Zisserman
Year 2010
PublicationType Journal Paper
Journal International Journal of Computer Vision
HostPublication
Conference
DOI http://dx.doi.org/10.1007/s11263-010-0353-7
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:537591
Abstract 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.