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
Understanding the Cortical Specialization for Horizontal Disparity
Neural Computation
Computing stereo disparity and motion with known binocular cell properties
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
Normalized phase shift motion energy neuron populations for image velocity estimation
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Disparity estimation by pooling evidence from energy neurons
IEEE Transactions on Neural Networks
Modeling stereopsis via markov random field
Neural Computation
Combining texture and stereo disparity cues for real-time face detection
Image Communication
| Hi-index | 0.00 |
Binocular fusion takes place over a limited region smaller than one degree of visual angle (Panum's fusional area), which is on the order of the range of preferred disparities measured in populations of disparity-tuned neurons in the visual cortex. However, the actual range of binocular disparities encountered in natural scenes extends over tens of degrees. This discrepancy suggests that there must be a mechanism for detecting whether the stimulus disparity is inside or outside the range of the preferred disparities in the population. Here, we compare the efficacy of several features derived from the population responses of phase-tuned disparity energy neurons in differentiating between in-range and out-of-range disparities. Interestingly, some features that might be appealing at first glance, such as the average activation across the population and the difference between the peak and average responses, actually perform poorly. On the other hand, normalizing the difference between the peak and average responses results in a reliable indicator. Using a probabilistic model of the population responses, we improve classification accuracy by combining multiple features. A decision rule that combines the normalized peak to average difference and the peak location significantly improves performance over decision rules based on either measure in isolation. In addition, classifiers using normalized difference are also robust to mismatch between the image statistics assumed by the model and the actual image statistics.