Share Email Print
cover

Proceedings Paper

Towards a real-time high-definition depth sensor with hardware-efficient stereo matching
Author(s): Ke Zhang; Guanyu Yi; C.-K. Liao; Christine Lin; Hsiu-Chi Yeh; Rudy Lauwereins; Luc Van Gool; Gauthier Lafruit
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, we present a hardware design of stereo matching for depth extraction. It is capable of matching high-definition images at real-time speed, producing high-quality disparity maps. The stereo algorithm comprises three major components, i.e. census transform, dynamic programming and local-adaptive voting. The census transform makes our method robust to radiometric differences. The dynamic programming method propagates information along scanlines by imposing a smoothness criterion. The local-adaptive voting further improves the matching quality, utilizing the correlation between intensity images and disparity maps. The whole algorithm is prototyped on a FPGA platform, effectively harnessing the power of parallel computing. With a working frequency of 65MHz, our design can produce high-quality 1024×768 disparity maps at 60fps.

Paper Details

Date Published: 25 February 2012
PDF: 8 pages
Proc. SPIE 8288, Stereoscopic Displays and Applications XXIII, 82882K (25 February 2012); doi: 10.1117/12.906574
Show Author Affiliations
Ke Zhang, IMEC (Belgium)
Katholieke Univ. Leuven (Belgium)
Guanyu Yi, Technische Univ. Delft (Netherlands)
C.-K. Liao, IMEC (Belgium)
Christine Lin, IMEC (Belgium)
Hsiu-Chi Yeh, Technische Univ. Delft (Netherlands)
Rudy Lauwereins, IMEC (Belgium)
Katholieke Univ. Leuven (Belgium)
Luc Van Gool, Katholieke Univ. Leuven (Belgium)
ETH Zurich (Switzerland)
Gauthier Lafruit, IMEC (Belgium)


Published in SPIE Proceedings Vol. 8288:
Stereoscopic Displays and Applications XXIII
Andrew J. Woods; Nicolas S. Holliman; Gregg E. Favalora, Editor(s)

© SPIE. Terms of Use
Back to Top