A Miniature Stereo Vision Machine for Real-Time Dense Depth Mapping

We have developed a miniature stereo vision machine (MSVM-2) to generate high-resolution dense depth map for application to portable intelligent robots and smart visual interface. The machine uses multiple cameras, each with a very wide field of view, to synchronously capture stereo image sequences, and then computes dense depth maps in real time. The whole algorithm, including radial distortion correction, LoG filtering, correspondence finding, and dense depth map computation, is compactly implemented in a single FPGA. The machine also has an IEEE 1394 port for video-rate data transferring to PCs and a parallel data interface port to other user-systems. The machine could achieve more than 30 frame-per-second processing rate for 640_ 480 dense depth map with a 64-pixel disparity search range and 8-bit depth precision, and up to 50 frame-per-second for a 320_ 240 depth map.

[1]  H. K. Nishihara.  Real-time stereo- and motion-based figure ground discrimination and tracking using LOG sign correlation , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[2]  Shigeru Kimura,et al.  A convolver-based real-time stereo machine (SAZAN) , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[3]  Paul R. Cohen,et al.  Camera Calibration with Distortion Models and Accuracy Evaluation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Laurent Moll,et al.  Real time correlation-based stereo: algorithm, implementations and applications , 1993 .

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

[6]  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).

[7]  Luigi di Stefano,et al.  A fast area-based stereo matching algorithm , 2004, Image Vis. Comput..

[8]  Takeo Kanade,et al.  A stereo machine for video-rate dense depth mapping and its new applications , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Peter Corke,et al.  Real-time stereopsis using FPGAs , 1997, TENCON '97 Brisbane - Australia. Proceedings of IEEE TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications (Cat. No.97CH36162).