Disparity estimation by pooling evidence from energy neurons

Authors:
Eric K. C. Tsang;Bertram E. Shi
Affiliations:
Hong Kong Applied Science and Technology Research Institute, Hong Kong and Department of Electrical and Computer Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowlo ...;Department of Electrical and Computer Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
Venue:
IEEE Transactions on Neural Networks
Year:
2009

Citing 8
Cited 0

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
A Bayesian approach to the stereo correspondence problem

Neural Computation
A coarse-to-fine disparity energy model with both phase-shift and position-shift receptive field mechanisms

Neural Computation
Computing stereo disparity and motion with known binocular cell properties

Neural Computation
Binocular receptive field models, disparity tuning, and characteristic disparity

Neural Computation
Dense depth map reconstruction by phase difference-based algorithm under influence of perspective distortion

Machine Graphics & Vision International Journal
Normalization enables robust validation of disparity estimates from neural populations

Neural Computation
High-accuracy stereo depth maps using structured light

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose an algorithm for disparity estimation from disparity energy neurons that seeks to maintain simplicity and biological plausibility, while also being based upon a formulation that enables us to interpret the model outputs probabilistically. We use the Bayes factor from statistical hypothesis testing to show that, in contradiction to the implicit assumption of many previously proposed biologically plausible models, a larger response from a disparity energy neuron does not imply more evidence for the hypothesis that the input disparity is close to the preferred disparity of the neuron. However, we find that the normalized response can be interpreted as evidence, and that information from different orientation channels can be combined by pooling the normalized responses. Based on this insight, we propose an algorithm for disparity estimation constructed out of biologically plausible operations. Our experimental results on real stereograms show that the algorithm outperforms a previously proposed coarse-to-fine model. In addition, because its outputs can be interpreted probabilistically, the model also enables us to identify occluded pixels or pixels with incorrect disparity estimates.