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.
Y. T. Zhou,
"Neural Network Approach To Stereo Matching", Proc. SPIE 0974, Applications of Digital Image Processing XI, (16 December 1988); doi: 10.1117/12.948464; https://doi.org/10.1117/12.948464