Illuminance Flow Estimation by Regression

Authors:
Stefan M. Karlsson;Sylvia C. Pont;Jan J. Koenderink;Andrew Zisserman
Affiliations:
IDE, Halmstad University, Halmstad, Sweden 30118;π-lab, Industrial Design Engineering, Delft University of Technology, Delft, The Netherlands 2628 CE;π-lab, Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands 2028 CD;Engineering Science, University of Oxford, Oxford, UK OX1 3PJ
Venue:
International Journal of Computer Vision
Year:
2010

Citing 12
Cited 0

Estimation of illuminant direction, Albedo, and shape from shading

Shape recovery
Vision texture for annotation

Multimedia Systems - Special issue on content-based retrieval
The nature of statistical learning theory

The nature of statistical learning theory
Making large-scale support vector machine learning practical

Advances in kernel methods
Simulation of wrinkled surfaces

SIGGRAPH '78 Proceedings of the 5th annual conference on Computer graphics and interactive techniques
Query by Image and Video Content: The QBIC System

Computer
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Classifying Surface Texture while Simultaneously Estimating Illumination Direction

International Journal of Computer Vision - Special Issue on Texture Analysis and Synthesis
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Comparison of Affine Region Detectors

International Journal of Computer Vision
Shape and source from shading

IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 2
Irradiation orientation from obliquely viewed texture

DSSCV'05 Proceedings of the First international conference on Deep Structure, Singularities, and Computer Vision

Quantified Score

Hi-index	0.00

Visualization

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.