A robust message passing based stereo matching kernel via system-level error resiliency

In this paper, we present an error resilient Markov random field (MRF) message passing based stereo matching hardware (HW) architecture. Previously, algorithmic noise tolerance (ANT) has been applied at the arithmetic level of the reparameterize unit and showed greatly enhanced robustness of message passing inference based architectures. In this work, correction was targeted at the system level to reduce correction overhead while maintaining performance. An erroneous FPGA based accelerator was employed as our emulation platform. Through relaxed synthesis, we show that timing errors occur within the message passing unit, and are successfully compensated. Error correction has been implemented at several hierarchical levels, including end of iteration, and the final depth map output. Significant enhancement in robustness is achieved with minimal correction overhead. Compared to HW error compensation at the arithmetic level, system level error compensation reduces overhead by more than 50 %, while maintaining stereo matching performance with only 3.8 % degradation.

[1]  Patrick Schaumont,et al.  An Analysis of Delay Based PUF Implementations on FPGA , 2010, ARC.

[2]  Nam Ik Cho,et al.  Low-Power Filtering Via Minimum Power Soft Error Cancellation , 2007, IEEE Transactions on Signal Processing.

[3]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[4]  William T. Freeman,et al.  Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Douglas L. Jones,et al.  Stochastic computation , 2010, Design Automation Conference.

[6]  Yücel Altunbasak,et al.  A collaborative multiple description transform coding and statistical error concealment method for error resilient video streaming over noisy channels , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Rob A. Rutenbar,et al.  Error resilient MRF message passing architecture for stereo matching , 2013, SiPS 2013 Proceedings.

[8]  Subhasish Mitra,et al.  ERSA: Error Resilient System Architecture for probabilistic applications , 2010, 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010).

[9]  Pedro F. Felzenszwalb,et al.  Efficient belief propagation for early vision , 2004, CVPR 2004.

[10]  Naresh R. Shanbhag,et al.  Reliable and efficient system-on-chip design , 2004, Computer.

[11]  Naresh R. Shanbhag,et al.  Energy-Efficient LDPC Decoders Based on Error-Resiliency , 2012, 2012 IEEE Workshop on Signal Processing Systems.

[12]  Heiko Hirschmüller,et al.  Evaluation of Cost Functions for Stereo Matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Rob A. Rutenbar,et al.  Video-Rate Stereo Matching Using Markov Random Field TRW-S Inference on a Hybrid CPU+FPGA Computing Platform , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[14]  Heiga Zen,et al.  Statistical Parametric Speech Synthesis , 2007, IEEE International Conference on Acoustics, Speech, and Signal Processing.

[15]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Vladimir Kolmogorov,et al.  Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.