Multiple Stereo Matching Using an Extended Architecture

In this paper, an FPGA based architecture for stereo vision is presented. The architecture provides a high-density disparity map in real time. The architecture is based on area comparison between an image pair using the sum of absolute differences. The architecture scans the input images in partial columns, which are then processed in parallel. The system performs monolithically on a pair of images in real time. An extension to the basic architecture is proposed in order to compute disparity maps on more than 2 images.

[1]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Kurt Konolige,et al.  Small Vision Systems: Hardware and Implementation , 1998 .

[3]  Takeo Kanade,et al.  Development of a Video-Rate Stereo Machine , 1997 .

[4]  Pascal Fua,et al.  Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities , 1991, IJCAI.

[5]  John Woodfill,et al.  Real-time stereo vision on the PARTS reconfigurable computer , 1997, Proceedings. The 5th Annual IEEE Symposium on Field-Programmable Custom Computing Machines Cat. No.97TB100186).

[6]  Miguel Arias-Estrada,et al.  Real-time FPGA-based architecture for stereo vision , 2001, IS&T/SPIE Electronic Imaging.