A System and Vision Localization Method for the Opening of Railway Oil Tank Wagon Based on Shape Matching

The opening localization for railway oil tank wagon using machine vision technology is an effective way to load petroleum automatically. In this paper, we introduce a localization system for the opening of railway oil tank wagon, which consists of industrial camera, lens, LED lighter, industrial PC, and IO module. In addition, we also propose a shape matching localization method, which can overcome the adverse effects produced by illumination changes, various types of railway oil tank wagon, and various poses of camera. The shape template is extracted from a standard opening image using edge detection and shape fitting methods, which can help avoid the randomness of template selection. An optimized similarity measure is exploited to avoid the edge extraction, so that the threshold setting of edge extraction can be avoided. In addition, we also exploit scalable template to find various types opening and exploit image pyramid during shape matching procedure to gain a speedup. The indoor and outdoor experiments show that the localization system and the proposed method fully meet the requirements of practical industrial applications.

[1]  Saumya Batham,et al.  Approach to accurate circle detection: Circular Hough Transform and Local Maxima concept , 2014, 2014 International Conference on Electronics and Communication Systems (ICECS).

[2]  Dmitry Chetverikov,et al.  Matching for Shape Defect Detection , 1999, CAIP.

[3]  Stan Z. Li.  Shape Matching Based on Invariants , 2007 .

[4]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..

[5]  Alexander M. Bronstein,et al.  Affine-invariant diffusion geometry for the analysis of deformable 3D shapes , 2010, CVPR 2011.

[6]  Mauro R. Ruggeri,et al.  Spectral-Driven Isometry-Invariant Matching of 3D Shapes , 2010, International Journal of Computer Vision.

[7]  Dmitry ChetverikovComputer.  Shape Defect Detection in Ferrite Cores , 1997 .

[8]  Xuezhi Xiang,et al.  A vision positioning method for the opening of railway oil tank wagon based on shape matching , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

[9]  Fang Xu,et al.  Industrial robot base assembly based on improved Hough transform of circle detection algorithm , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

[10]  Hamid Laga,et al.  Covariance-Based Descriptors for Efficient 3D Shape Matching, Retrieval, and Classification , 2015, IEEE Transactions on Multimedia.

[11]  Li Shang,et al.  Shape matching and object recognition using common base triangle area , 2015, IET Comput. Vis..

[12]  Carsten Steger,et al.  Similarity Measures for Occlusion, Clutter, and Illumination Invariant Object Recognition , 2001, DAGM-Symposium.

[13]  Jan-Olof Eklundh,et al.  Shape Representation by Multiscale Contour Approximation , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Markus Ulrich,et al.  Performance Evaluation of 2D Object Recognition Techniques , 2002 .

[15]  Feng Chi.  Design of vision positioning system for opening of train tank , 2006 .

[16]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[17]  Gunilla Borgefors,et al.  Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Yaobin Mao,et al.  A real-time and robust multi-circle detection method based on randomized Hough transform , 2012, 2012 International Conference on Computer Science and Information Processing (CSIP).

[19]  Luigi di Stefano,et al.  An efficient algorithm for exhaustive template matching based on normalized cross correlation , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[20]  Stefano Soatto,et al.  Shape Matching Using Multiscale Integral Invariants , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Xin Zhou,et al.  An Efficient Implementation of the One-Dimensional Hough Transform Algorithm for Circle Detection on the FPGA , 2014, 2014 Second International Symposium on Computing and Networking.

[22]  Ahmed Elhossini,et al.  Memory efficient FPGA implementation of hough transform for line and circle detection , 2012, 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).