VoC: a reconfigurable matrix for stereo vision processing

Authors:
Ricardo P. Jacobi;Renato B. Cardoso;Geovany A. Borges
Affiliations:
University of Brasilia, Dept. of Computer Science, Brasilia, Brazil;University of Brasilia, Dept. of Electrical Engineering, Brasilia, Brazil;University of Brasilia, Dept. of Electrical Engineering, Brasilia, Brazil
Venue:
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Year:
2006

Citing 7
Cited 4

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
A Hierarchical Symmetric Stereo Algorithm Using Dynamic Programming

International Journal of Computer Vision
Real-time stereo vision on the PARTS reconfigurable computer

FCCM '97 Proceedings of the 5th IEEE Symposium on FPGA-Based Custom Computing Machines
Trinocular Stereo: A Real-Time Algorithm and Its Evaluation

SMBV '01 Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV'01)
Tyzx DeepSea High Speed Stereo Vision System

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 3 - Volume 03
Video-rate stereo depth measurement on programmable hardware

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Multi-resolution real-time stereo on commodity graphics hardware

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

RASCor: An associative hardware algorithm for real time stereo

Computers and Electrical Engineering
Flexible hardware-based stereo matching

EURASIP Journal on Embedded Systems - Special issue on design and architectures for signal and image processing
Leveraging cost matrix structure for hardware implementation of stereo disparity computation using dynamic programming

Computer Vision and Image Understanding
A reconfigurable disparity engine for stereovision in advanced driver assistance systems

ARC'10 Proceedings of the 6th international conference on Reconfigurable Computing: architectures, Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a reconfigurable matrix VoC that can be applied to stereo vision computation. VoC accelerates block pixel matching by providing a highly parallel implementation of the Sum of Absolute Differences metric. Reconfigurability allows VoC to deal with different block sizes, ranging from a single 7×7 SAD computation to 9 simultaneous 5x5 block computations. The pipelined version mapped to Xilinx FPGA could be simulated at 158 MHz, producing 1,42 billion matchings per second.