期刊文献+

形变冗余的改进GHT目标双层定位方法研究 被引量:2

Two-level deformed target locate algorithm based on the variant of generalized Hough transform
原文传递
导出
摘要 经典广义Hough变换可以较好地解决非形变目标定位问题,但对于存在形变的目标定位问题存在不少困难。为解决该问题,同时考虑如何提高检测定位速度与减少存储消耗,在粗定位与精确定位两级框架下提出基于改进GHT形变目标两层定位快速算法。粗定位过程首先利用图像的局域二进制模式的直方图特征对图像进行全局搜索,检测出目标大致范围;在精确定位过程中,通过建立模板图像边缘像素的R表,使待检测图像边缘像素在约束的参数范围内依据该R表进行局部搜索,并通过一个投票结果散布窗对得到的累积矩阵进行集中化处理,达到把每一点邻域内投票结果集中在某点的目的,从而给出最后的检测结果。实验表明,本文算法能够较好的解决一定程度形变目标的定位问题,同时减少了运算时间以及存储消耗,检测稳定性高,具有一定应用意义。 Classic generalized Hough transform (GHT) can locate non-deformed shape object, while it is difficult to solve the problem when the target is similar but not necessarily identical to the user or deformation. A two level deformed target locate algorithm based on variant of the well-known GHT for solving this problem is presented. Firstly .a two-level locationscheme from coarse to fine strategy is introduced to reduce search range from whole image space, in coarse location step, the edge local binary pattern (LBP) histogram features are extracted to detect the range of the target. In fine location step, making use of the edge points of the image detected and the R-table obtained from the template image to search the feasible parameter, and a large dispersion window used to merge vote results because there is non-perfectly aligned points near the optimal parameters. The experiment results demonstrate that the method is effective to the deformed target locating while time and memory cost is much less, and it is valuable in many applications.
出处 《中国图象图形学报》 CSCD 北大核心 2011年第1期50-58,共9页 Journal of Image and Graphics
基金 国家自然科学基金项目(61071199) 河北省自然科学基金项目(F2008000891) 河北省自然科学基金项目(F2010001297) 中国博士后自然科学基金项目(20080440124) 第二批中国博士后基金项目(200902356)
关键词 广义HOUGH变换 局域二进制模式直方图特征 目标定位 累积矩阵 generalized Hough transform local binary pattern histogram object location accumulator matrix
  • 相关文献

参考文献9

  • 1张凯,王瑜辉,尹周平,熊有伦.应用在高性能贴片机上的一种快速视觉定位算法[J].光学技术,2005,31(4):604-607. 被引量:7
  • 2Ballard D H. Generalizing the Hough transform to detect arbitrary shapes [J]. Pattern Recognition, 1981,13( 2): 111-122.
  • 3Tipwai P, Madarasmi S. A modified generalized Hough transform for image search [ J ]. IEICE Transactions on Information and Systems, 2007, E90- D(1): 165-172.
  • 4Anelli M, Cinque L, Sangineto E. Deformation tolerant generalized Hough transform for sketch-based image retrieval in complex scenes [ J]. Image and Vision Computing, 2007, 25(11) : 1802-1813.
  • 5Aquado A S, Euqenia M, Nixon M S. Invafiant characterisation of the Hough transform for pose estimation of arbitrary shapes [J].Pattern Recognition, 2002, 35 (5) : 1083-1097.
  • 6Gonzalez-Linares J M, Guil N, Zapata E L. An efficient 2D deformable objects detection and location algorithm [ J]. Pattern Recognition, 2003,36 (3) : 2543 -2556.
  • 7李智磊,翟宏琛,王明伟.一种可识别破碎图形的特殊广义Hough变换方法[J].物理学报,2007,56(6):3234-3239. 被引量:15
  • 8Tsai D M. An improved generalized Hough transform for the recognition of overlapping objects [J].Image and Vision Computing, 1997,15(3) : 877-888.
  • 9Zhang Hongming, Wen Gao, Chen Xilin, et al. Object detection using spatial histogram features [ J ]. Image and Vision Computing, 2006, 24(4): 327-341.

二级参考文献14

  • 1申金媛,李现国,常胜江,张延炘.相位特征在三维物体识别中的应用[J].物理学报,2005,54(11):5157-5163. 被引量:8
  • 2Cooper K A, Yang R, Mottet J S, et al. Flip chip equipment for high end electro-optical modules [ A]. Electronic and Components Technology Conference[C]. America: IEEE, 1998.
  • 3Gillbertt Learpentier, Jean-Stephane Mottetet, Jeffrey Dumas, et al. High accuracy machine automated assembly for opto electronics[A]. Electronic and Components Technology Conference [C].America: IEEE, 2000.
  • 4GonzalezRC.Woods R E数字图像处理[M].北京:电子工业出版社,2003..
  • 5Ren H P,Ping Z L,Bo W R G,Sheng Y L,Chen S Z,Wu W K 2003 Chin.Phys.12 610
  • 6Ballard D H 1981 Pattern Recognition 13 111
  • 7Lee H M,Kittler J,Wong K C 1992 11th IAPR International Conference on Pattern Recognition 3 285
  • 8Beinglass A,Wolfson H J 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 461
  • 9Wong K C,Sim H C,Kittler J 1995 Inter.Confer.on Image Process.3 376
  • 10Chau C P,Siu W C 2004 Inter.J.of Computer Vision 59(2) 183

共引文献20

同被引文献32

  • 1杨翠茹.基于纹理特征的绝缘子检测方法[J].电气技术,2010,11(7):46-48. 被引量:13
  • 2SUNSIN H, RU H, JANGMYUNG L. Inspection of insu- lators on high-voltage power transmission lines [ J ]. IEEE Transactions on Power Delivery, 2009, 24 ( 4 ) : 2319-2327.
  • 3ZHANG J, YANG R Q. Irrtdators rognization for 220kV/ 330 kV high-wltage live-line cleaning[ C]. The 18th Interna- tional Conference on Pattern Recognization, 21306 (4): 630-633.
  • 4黄珊珊,钱政.智能电网中输电线路绝缘子在线检测方法综述[J].仪器仪表学报,2010,31(增刊):159.163.
  • 5TING F, ZHAO Y B, HU X L, et al. An improved meanshift insulator image segmentation algorithm [ J ]. Advanced Materials Research, 2013, 634-638 : 3945 -3949.
  • 6KHALAYLI L, SAGBAN H A, SHOMAN H, et al. Au- tomatic inspection of outdoor insulators using image pro- cessing and intelligent techniques [ C ]. IEEE Electrical Insulation Conference, 2013 : 206-209.
  • 7WU Q G, AN J B, LIN B. A texture segmentation algo- rithm based on PCA and global minimization active con- tour model for aerial insulator images [ J ]. IEEE Journal Selected Topics in Applied Earth Observations and Re- mote Sensing, 2012.5 ( 1 ) : 1509-1518.
  • 8CUNHA A L, ZHOU J P, DO M N. The nonsubsam- pied Contourlet transform: Theory, design, and appli- cations[ J]. IEEE Transactions on Image Processing, 2006,15(10) : 3089-3101.
  • 9KORANI W M, DORRAH H T, EMARA H M. Bacterial foraging oriented by particle swarm optimization strategy for PID tuning [ C ]. IEEE International Symposium on Computational Intelligence in Robotics and Automation, 2009 : 445-450.
  • 10KULKARNI R V, VENAYAGAMOORTHY G K. Bio-in- spired algorithms for autonomous deployment and localiza- tion of sensor nodes[ J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Re- views, 2010, 40(6) : 663-675.

引证文献2

二级引证文献51

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部