Stereo vision implementation
Naim Dahnoun · 2017
Moving from 2D to 3D representation of an object or a scene can offer an unparalleled advantage since it provides depth information. Stereo vision systems work in the same way as the human vision system which is composed of two eyes and a brain (two cameras and a processor). However, these systems cannot match the human vision system and therefore need to be limited to specific applications to improve the performance. The two main features of a stereoscopic system are the speed (real-time) and accuracy (quality). To calculate the disparity is to select a pixel on one image, find its corresponding pixel on the other image and measure the distance between these two pixels. This chapter shows the principle behind the stereo vision system and highlights different levels of optimisations for achieving real-time performance. Some techniques for reducing the processing time for calculating disparity values for automotive applications are also introduced.