A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces

摘要

For recovering precise object boundaries in area-based stereo matching, there are two problems. One is the so-called “occlusion problem”. This can be avoided if we can select only “visible” cameras among many cameras used. Another one is the problem called “boundary overreach”, i.e. the recovered object boundary turns out to be wrongly located away from the real one due to the window's coverage beyond a boundary. This is especially harmful to segmenting objects using depth information. A few approaches have been proposed to solve this problem. However, these techniques tend to degrade on smooth surfaces. That is, there seems to be a trade-off problem between recovering precise object edges and obtaining smooth surfaces.