Difference between revisions of "Publications:Illuminance Flow Estimation by Regression"
From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Stefan Karlsson, Sylvia C. Pont, Jan J. Koenderink, Andrew Zisserman |PID=5...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Stefan Karlsson, Sylvia C. Pont, Jan J. Koenderink, Andrew Zisserman | {{PublicationSetupTemplate|Author=Stefan Karlsson, Sylvia C. Pont, Jan J. Koenderink, Andrew Zisserman | ||
|PID=537591 | |PID=537591 | ||
| − | |Name=Karlsson, Stefan M. | + | |Name=Karlsson, Stefan M. (stekar) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938));Pont, Sylvia C. ( Pi-Lab., Industrial Design Engineering, Delft University of Technology, Landbergstraat 15, Delft 2628 CE, Netherlands);Koenderink, Jan J. (Pi-Lab., Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Mekelweg 4, Delft 2028 CD, Netherlands);Zisserman, Andrew (Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, United Kingdom) |
|Title=Illuminance Flow Estimation by Regression | |Title=Illuminance Flow Estimation by Regression | ||
|PublicationType=Journal Paper | |PublicationType=Journal Paper | ||
Latest revision as of 21:40, 30 September 2016
| 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. |
