一种基于几何特征的列车集尘器形状匹配算法

摘要/Abstract

摘要：

针对列车集尘器定位不准确的问题，提出了一种基于几何特征的形状匹配算法。该算法首先对轮廓点进行采样，基于极半径、局部曲率确定关键点的初始位置及点集的映射关系，然后以形心为基准，生成以角度和尺度为几何特征的双重描述子，并对其作标准量化处理。最后使用改进的曼哈顿距离计算描述子的相似性。实验结果表明,该形状匹配算法几乎不受伸缩、旋转、平移等几何变换的影响，具有一定的适应性和鲁棒性。

关键词: 货车故障图像检测系统, 集尘器, 几何特征, 形状匹配, 描述子

Abstract:

Due to the problem of inaccurate positioning of the train dust collector,a shape matching method was proposed based on geometric features.Firstly,the contour points were sampled and initial location of critical points and mapping relations of point sets were determined based on polar radius and local curvature.Then taking centroid as a benchmark,dual descriptors with geometric features of angles and scales were generated and processed by standard quantification.Finally, the similarity of the descriptors was calculated with modified Manhattan distance.The experimental results show that the proposed shape matching method is harldy influenced by geometric transformation such as scale, rotation,and translation, which demonstrates its adaptability and robust.

Key words: trouble of moving freight car detection system(TFDS), dust collector, geometric feature, shape matching, descriptor

中图分类号:

TP29

孙国栋, 杨林杰, 梅术正, 赵大兴. 一种基于几何特征的列车集尘器形状匹配算法[J]. 中国机械工程, 2016, 27(02): 230-234,257.

Sun Guodong, Yang Linjie, Mei Shuzheng, Zhao Daxing. A Shape Matching Method for Train Dust Collector Based on Geometrical Features[J]. China Mechanical Engineering, 2016, 27(02): 230-234,257.

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): 890-910.
Zhou Yu,Liu Juntao,Bai Xiang.Research and Perspective on Shape Matching[J].Acta Automatica Sinica,2012, 38(6):879-910.
[2]孙国栋, 徐威, 梁永强, 等. 基于形状上下文的列车挡键丢失图像识别算法[J].铁道科学与工程学报, 2014, 11(6): 127-131.
Sun Guodong, Xu Wei, Liang Yongqiang, et al. Image Recognition Algorithm for Side Frame Key of Train Based on Shape Context[J]. Journal of Railway Science and Engineering, 2014, 11(6):127-131.
[3]王英, 陈建能, 赵雄, 等. 基于NURBS曲线的凸轮廓线表达方法的研究及应用[J].中国机械工程，2013,24(10)：1375-1379.
Wang Ying,Chen Jianneng,Zhao Xiong,et al.Study on Cam Profile's Expression Method and Its Applications Based on NURBS Curves[J]. China Mechanical Engineering, 2013 ,24(10)：1375-1379.
[4]Belongie S, Malik J, Puzicha J.Shape Matching and Object Recognition Using Shape Contexts[J].IEEE Transactionson Pattern Analysis and Machine Intelligence, 2002, 24(4): 509-522.
[5]孙晓鹏, 李思慧, 王璐. 耳廓点云形状特征匹配的路径跟随算法[J].软件学报, 2015, 26(5): 1251-1264.
Sun Xiaopeng, Li Sihui, Wang Lu.Shape Feature Matching Algorithm of Ear Point Cloud Using Path Following[J]. Journal of Software, 2015, 26(5):1251-1264.
[6]肖爱玲, 潘斌. 基于标记的极半径极值红枣形状识别方法[J].农机化研究, 2015(7):61-65.
Xiao Ailing，Pan Bin. Identification of the Shape of Chinese Date Based on Labelling Method and Extremum of Polar Radius [J]. Journal of Agricultural Mechanization Research, 2015(7): 61-65.
[7]Steger C,Uirich M,Weedemann C.Machine Vision Algorithms and Application[M].Beijing:Tsinghua University Press, 2008.
[8]王斌.一种不变的基于傅里叶变换的区域形状描述子[J].电子学报, 2012, 40(1): 84-88.
Wang Bin.An Invariant Region-shape Descriptor Based on Fourier Transform[J].Acta Electronica Sinica, 2012, 40(1): 84-88.
[9]崔峰, 汪雪林, 彭思龙.近似欧氏距离变换的一种并行算法[J].中国图象图形学报,2004,9(6):693-698.
Cui Feng, Wang Xuelin, Peng Silong.A Parallel Algorithm for Quasi Euclidean Distance Transform[J]. Journal of Image and Graphics, 2004, 9(6): 693-698.
[10]徐少平, 张华, 江顺亮, 等. 基于直觉模糊集的图像相似性度量[J].模式识别与人工智能,2009,22(1):156-161.
Xu Shaoping, Zhang Hua,Jiang Shunliang,et al.Image Similarity Measure Based on Intuitionistic Fuzzy Set [J]. Pattern Recognition and Artificial Intelligence, 2009, 22(1): 156-161.
[11]赵大兴, 王璜, 朱锦雷, 等.高精度自适应阈值分割算子的设计[J].计算机应用, 2008, 28(7): 1742-1743.
Zhao Daxing, Wang Huang, Zhu Jinlei, et al. Design of Thresholding Segmentation Operator with High Precision Self-adaptive Capacity [J]. Computer Applications, 2008, 28(7):1742-1743.