An Extraction Method of Steel Plate Surface Depth Information Based on Image Pyramid
LIU Yuan-jiong1,KONG Jian-yi1,XU Fu-jun2,HUANG Qian-de1,WANG Xing-dong1
1. MoE Key Laboratory of Metallurgical Equipment and Their Control, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China;
2. Wuxi Courier Machinery Co., Ltd, Yixing, Jiangsu 214221, China
Abstract：To satisfy the requirement of both precision and real-time of traditional region matching algorithms, a region-based hierarchical matching algorithm based on the mean image pyramid was proposed combining with the normalized cross correlation method. The algorithm has been controlled efficiently through the parameters such as matching window size, the smallest eigenvalue, and the disparity search space, similarity measure threshold, etc. The extraction of steel plate surface depth information was realized by the ways of camera calibration of binocular stereo vision system and image correction based on equivalent standard epipolar structure. The experiment results showed that the algorithm yields better accuracy and higher efficiency.
［1］Blahusch G,Eckstein W, Steger C. Calibration of Curvature of Field for Depth From Focus［J］. ISPRS Archives, 2003,34:17-19.
［2］Lindner C, Leon F P. Model-Based Segmentation of Surfaces Using Illumination Series［J］. IEEE Transactions On Instrumentation And Measurement, 2007,56(4):1340-1346.
［3］Stefano L D, Mattoccia S, Mola M. An efficient algorithm for exhaustive template matching based on normalized cross correlation［C］// Proceedings of 12th International conference on Image Analysis and Processing, Mantova, Italy, 2003: 322-327.
［4］Stefano L D, Marehionni M, Mattoccia S. A Fast Area-Based Stereo Matching Algorithm［J］. Image and Vision Computing, 2004, 22(12):983-1005.
［5］Daniel S, Szeliski R. Stereo matching with nonlinear diffusion［J］. International Journal of Computer Vision, 1998, 28(2): 155-174.
［6］ 郭龙源. 计算机视觉立体匹配相关理论与算法研究［D］. 南京:南京理工大学, 2009.
［7］Veksler O. Fast variable window for stereo correspondence using integral images［C］// Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Madison, WI, USA, 2003: 556-561.
［8］张广军. 机器视觉［M］. 北京:科学出版社, 2005.
［9］刘源泂,孔建益,王兴东,等.双目立体视觉系统的非线性摄像机标定技术［J］. 计算机应用研究, 2011, 28(9):3398-3400.
［10］Faugeras O. Three-Dimensional Computer Vision: A Geometric Viewpoint［M］. Cambridge, MA: MIT Press, 1993.
［11］Gonzalez R C, Woods R E. 数字图像处理(第3版)［M］. 阮秋琦,等译. 北京: 电子工业出版社, 2010.
［12］Shahiduzzaman M, Zhang D S, Lu G J. Improved Spatial Pyramid Matching for Image Classification［C］// Proceedings of ACCV 2010,Queenstown, New Zealand, Part IV: 449–459.
［13］Zhang K,Wang H M,Li Y J. A Robust Steerable Pyramid Based Image Matching Algorithm［J］. Journal of Astronautics, 2005, 26(6): 717-723.
［14］Tanimoto S L.Template matching in pyramids［J］. Computer Graphics and Image Processing, 1981, 16: 356-369.
［15］高文,陈熙霖. 计算机视觉、算法与系统原理［M］. 北京: 清华大学出版社, 1999.
［16］Steger C, Ulrich M, Wiedemann C. Machine Vision Algorithms and Applications［M］. Germany: Wiley-VCH, Weinheim, 2007.
2015, Vol. 36 
