Computational Experiments with a Feature Based Stereo Algorithm

TLDR

Computational models of the human stereo system, such as Marr and Poggio’s 1977 feature‑matching approach, provide insight into general information‑processing constraints and have been refined by psychophysical experiments and recent studies on natural images, especially aerial photographs. This paper presents a version of the Marr‑Poggio‑Grimson algorithm that incorporates these refinements. The authors illustrate the algorithm’s performance on a series of natural images. An implementation of the algorithm and its testing on a range of images was reported in 1980.

Abstract

Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977 Marr and Poggio proposed one such computational model, which was characterized as matching certain feature points in difference-of-Gaussian filtered images and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Since then a number of psychophysical experiments have suggested possible refinements to the model and modifications to the algorithm. As well, recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this paper, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and we illustrate its performance on a series of natural images.