Measuring distance to obstacles is an important process for intelligent vehicles (IV). With accurate measurement, IV can make appropriate maneuver to avoid such obstacles. To obtain highly accurate result, we used a Markov random field model-based global energy minimization algorithm called belief propagation (BP). However, BP has high computational complexity which makes it difficult for real-time processing. To solve this issue, we took massively parallel approach using Compute Unified Device Architecture (CUDA). In this paper, we first provide profiling result to find the performance bottleneck of BP. Next, we explain CUDA-specific optimization techniques to enhance the performance. We propose a new parallelization technique to speed up the message computation, which takes up the longest time in BP. The experimental result shows that we were able to obtain accurate distance estimation result in real time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CUDA implementation of belief propagation for stereo vision


    Contributors:


    Publication date :

    2010-09-01


    Size :

    427100 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Acyclic belief propagation for stereo matching

    Piovano, L. / Balossino, N. / Lucenteforte, M. et al. | British Library Online Contents | 2009


    Dense photometric stereo using tensorial belief propagation

    Kam-Lun Tang, / Chi-Keung Tang, / Tien-Tsin Wong, | IEEE | 2005



    Globally Optimal Solutions for Energy Minimization in Stereo Vision Using Reweighted Belief Propagation

    Meltzer, T. / Yanover, C. / Weiss, Y. et al. | British Library Conference Proceedings | 2005


    Real-time stereo matching based on fast belief propagation

    Xiang, X. | British Library Online Contents | 2012