激光与光电子学进展, 2016, 53 (4): 041501, 网络出版: 2016-03-25   

基于多边形拟合的形状匹配与定位算法研究 下载: 1414次

Study of Shape Matching and Localization Algorithm Based on Polygon Fitting
作者单位
华中科技大学材料成形与模具技术国家重点实验室, 湖北 武汉 430074
摘要
基于机器视觉的加工控制过程中,对工件上待加工点的定位是关键,其难点在于构建一种形状描述方法,既要能实现形状匹配,又要能完成定位,且满足加工过程中的精度和实时性要求。为解决上述问题,提出了一种基于多边形拟合的形状匹配和定位算法。该方法针对平面二维(2D)轮廓,通过对轮廓进行多边形拟合,获取轮廓上关键点,然后构建形状描述子用于形状匹配,再利用这些关键点坐标进行定位计算,获得模板轮廓到目标轮廓的变换关系。结果表明,通过运用所提出的旋转不变性形状描述算法,可获得高精度、高实时性的形状匹配和定位算法。
Abstract
In the control procedure of process based on machine vision, the key is the location of the special point on work piece. The difficulty lies in how to construct a shape descriptor that can meet the needs of shape matching, precision of location and real-time at the same time. To solve the problems above,a kind of shape matching and localization algorithm based on polygon fitting is proposed. The method is aimed at the planar two-dimension (2D) contour. The key points on the contour are gained by the polygon fitting processing, then the polygon is used to construct a shape description and the key points are used to make location, to obtain the transformation relationship between template contour and target contour. The results show that by using the proposed rotation invariant shape descriptor, high accuracy and good real-time performance of shape matching and location algorithm can be gained.
参考文献

[1] 周瑜, 刘俊涛, 白翔. 形状匹配方法研究与展望[J]. 自动化学报, 2012, 38(6): 889-910.

    Zhou Yu, Liu Juntao, Bai Xiang. Research and perspective on shape matching[J]. Acta Automatica Sinica, 2012, 38(6): 889-910.

[2] 丁险峰, 吴洪, 张宏江, 等. 形状匹配综述[J]. 自动化学报, 2001, 27(5): 678-694.

    Ding Xianfeng, Wu Hong, Zhang Hongjiang, et al.. Review on shape matching[J]. Acta Automatica Sinica, 2001, 27(5): 678-694.

[3] 王军伟. 融合全局与局部信息的形状轮廓特征分析与匹配[D]. 武汉: 华中科技大学, 2012.

    Wang Junwei. Research on shape contour analysis and matching based on combined global and local information[D]. Wuhan: Huazhong University of Science and Technology, 2012.

[4] 刘濛, 吴成东, 王力, 等. 复杂背景图像中的车牌定位算法[J]. 中国图象图形学报, 2010, 15(9): 1357-1362.

    Liu Meng, Wu Chengdong, Wang Li, et al.. License plate position algorithm in complicated scenes[J]. Journal of Image and Graphics, 2010, 15(9): 1357-1362.

[5] Lowe D G. Distinctive image features from scale- invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

[6] 傅卫平, 秦川, 刘佳, 等. 基于SIFT 算法的图像目标匹配与定位[J]. 仪器仪表学报, 2011, 32(1): 163-169.

    Fu Weiping, Qin Chuan, Liu Jia, et al.. Matching and location of image object based on SIFT algorithm[J]. Chinese Journal of Scientific Instrument, 2011, 32(1): 163-169.

[7] 侯一民, 隋文秀, 孙晓雪. SIFT 特征降维方法及其在图像检索中的应用[J]. 中国激光, 2015, 42(s1): s108002.

    Hou Yimin, Sui Wenxiu, Sun Xiaoxue. SIFT feature drmension reduction method and its application in image retrieval [J]. Chinese J Lasers, 2015, 42(s1): s108002.

[8] 顾国庆, 白瑞林, 杜斌. 基于角点匹配的几何形状定位[J]. 江南大学学报(自然科学版), 2011, 10(2): 140-144.

    Gu Guoqing, Bai Ruilin, Du Bin. Geometry shape position based on point feature matching[J]. Journal of Jiangnan University (Natural Science Edition), 2011, 10(2): 140-144.

[9] Douglas D H, Peucker T K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature[M]. John Wiley & Sons, Ltd, 2011.

[10] Evans A, Thacker N A, Mayhew J E W. The use of geometric histograms for model-based object recognition[C]. BMVC, 1993, 93: 429-438.

[11] Huet B, Hancock E R. Relational histograms for shape indexing[C]. Sixth International Conference on Computer Vision, 1998: 563569.

[12] 杨镠, 郭宝龙, 李雷达, 等. 基于图像几何特征点的仿射参数估计算法研究[J]. 计算机科学, 2009, 36(6): 279-281.

    Yang Liu, Guo Baolong, Li Leida, et al.. Research on evaluation of affine parameter estimation using image feature points[J]. Computer Science, 2009, 36(6): 279-281.

白宇, 张李超, 史玉升, 鄢然. 基于多边形拟合的形状匹配与定位算法研究[J]. 激光与光电子学进展, 2016, 53(4): 041501. Bai Yu, Zhang Lichao, Shi Yusheng, Yan Ran. Study of Shape Matching and Localization Algorithm Based on Polygon Fitting[J]. Laser & Optoelectronics Progress, 2016, 53(4): 041501.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!