Neural Network Approach To Stereo Matching

Yi Zhou, Rama ChellappaProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 1988 · DOI

Abstract

A method for matching stereo images using a neural network is presented. We first fit a polynomial to find a smooth continuous intensity function in a window and estimate the first order intensity derivatives. Combination of smoothing and differentiation results in a window operator which functions very similar to the human eye in detecting the intensity changes. Since natural stereo images are usually digitized for the implementation on a digital computer, we consider the effect of spatial quantization on the estimation of the derivatives from natural images. A neural network is then employed for matching the estimated first order derivatives under the epipolar, photometric and smoothness constraints. Owing to the dense intensity derivatives a dense array of disparities is generated with only a few iterations. This method does not require surface interpolation. Experimental results using natural images pairs are presented to demonstrate the efficacy of our method.
BibTeX
@inproceedings{zhou1988neural,
  author = {Yi Zhou and Rama Chellappa},
  title = {{Neural Network Approach To Stereo Matching}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {1988},
  doi = {10.1117/12.948464},
}

Loading related content...

Figure