Fast and robust stereo matching algorithms for mining automation

The mining environment, being complex, irregular, and time-varying, present s a challenging prospect for stereo vision. For this application, speed, re liability, and the ability to produce a dense depth map are of foremost imp ortance. This paper evaluates a number of matching techniques for possible use in a stereo vision sensor for mining automation applications. Area-base d techniques have been investigated because they have the potential to yiel d dense maps, are amenable to fast hardware implementation, and are suited to textured scenes. In addition, two nonparametric transforms, namely, rank and census, have been investigated. Matching algorithms using these transf orms were found to have a number of clear advantages, including reliability in the presence of radiometric distortion, low computational complexity, a nd amenability to hardware implementation. (C) 1999 Academic Press.