Accurate Objects Detection Using Stereo Vision Sensor for Machine Vision Applications

  • Authors

    • RA. Hamzah
    • MGY. Wei
    • NS. Nik Anwar
    • AF. Kadmin
    • SF. Abd Gani
    • MS Hamid
    https://doi.org/10.14419/ijet.v7i4.11.20679

    Received date: September 30, 2018

    Accepted date: September 30, 2018

    Published date: October 2, 2018

  • matching algorithm, machine vision, object detection.

  • Abstract

    This paper presents a new algorithm for object detection using a stereo camera system, which is applicable for machine vision applications. The propose algorithm has four stages which the first stage is matching cost computation. This step acquires the preliminary result using a pixel based differences method. Then, the second stage known as aggregation step uses a guided filter with fixed window support size. This filter is efficiently reduce the noise and increase the edge properties. After that, the optimization stage uses winner-takes-all (WTA) approach which selects the smallest matching differences value and normalized it to the disparity level. The last stage in the framework uses a bilateral filter, which is effectively further reduce the remaining noise on the disparity map. This map is two-dimensional mapping of the final result which contains information of object detection and locations. Based on the standard benchmarking stereo dataset, the proposed work produces good results and performs much better compared with some recently published methods.

  • References

    1. Hamzah R A, Hamid M S, Kadmin A F, Ghani S A, Salam S. Dispari-ty map algorithm based on edge preserving filter for stereo video pro-cessing. Journal of Telecommunication, Electronic and Computer En-gineering, 2018, 1210(1-7), 59-62.
    2. Hamzah R A, Aziz K A A, and Shokri A S M. A pixel to pixel corre-spondence and region of interest in stereo vision application. Pro-ceedings of the IEEE Symposium on Computers and Informatics, 2012, pp. 193-197.
    3. Wu S S, Tsai H, and Chen L G. Efficient hardware architecture for large disparity range stereo matching based on belief propagation. Proceedings of the IEEE International Workshop on Signal Processing Systems, 2016, pp. 236–241.
    4. Hamzah R A, Ibrahim H, and Hassan A H A. Stereo matching algo-rithm based on per pixel difference adjustment, iterative guided filter and graph segmentation. Journal of Visual Communication and Image Representation, 2017, 42, 145–160.
    5. Gudis E, van der Wal G, Kuthirummal S, Chai S, and Kumar R. Ste-reo vision embedded system for augmented reality. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pat-tern Recognition Workshops, 2012, pp. 15-20.
    6. Balter M L, Chen A I, Maguire T J and Yarmush M L. Adaptive kin-ematic control of a robotic venipuncture device based on stereo vi-sion, ultrasound, and force guidance. IEEE Transactions on Industrial Electronics, 2017, 64(2), 1626-1635.
    7. Scharstein D, Szeliski R, and Zabih R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision, 2001, pp. 131–140.
    8. Liang Q, Yang Y, and Liu B. Stereo matching algorithm based on ground control points using graph cut. Proceedings of the Internation-al Congress on Image and Signal Processing, 2014, pp. 503–508.
    9. Hamzah RA, Kadmin AF, Hamid MS, Ghani SF, Ibrahim H. Im-provement of stereo matching algorithm for 3D surface reconstruc-tion. Signal Processing: Image Communication, 2018, 65, 165-172.
    10. Zbontar J and LeCun Y. Computing the stereo matching cost with a convolutional neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1592–1599.
    11. Hu W, Zhang K, Sun L, Li J, and Yang S. Virtual support window for adaptive-weight stereo matching. IEEE Visual Communications and Image Processing, 2011, pp. 1–4.
    12. Einecke N and Eggert J. Anisotropic median filtering for stereo dis-parity map refinement. Proceedings of the International Conference on Computer Vision Theory and Applications, 2013, pp. 189–198.
    13. He K, Sun J, and Tang X. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6), 1397–1409.
    14. Hamzah R A, Kadmin A F, Ghani S F A, Hamid M S, and Salam S. Disparity refinement process based on RANSAC plane fitting for ma-chine vision applications. Journal of Fundamental and Applied Sci-ences, 2017, 9(4S), 226-237.
    15. Scharstein D and Szeliski R. Middlebury stereo evaluation - version 3. http://vision.middlebury.edu/stereo/eval/references.
    16. Menze M and Geiger A. Object scene flow for autonomous vehicles. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3061–3070.
    17. Hamzah R A, Ibrahim H. Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi global method with refinement step. Electronics Letters, 2018, 54(14), 876–878

  • Downloads

  • How to Cite

    Hamzah, R., Wei, M., Nik Anwar, N., Kadmin, A., Abd Gani, S., & Hamid, M. (2018). Accurate Objects Detection Using Stereo Vision Sensor for Machine Vision Applications. International Journal of Engineering and Technology, 7(4.11), 9-12. https://doi.org/10.14419/ijet.v7i4.11.20679