[1]HUANG Yueyu,ZHOU Hang,CHEN Yehong,et al.TEDS underbody fault location algorithm in virtue of weak texture matching[J].CAAI Transactions on Intelligent Systems,2024,19(3):670-678.[doi:10.11992/tis.202303006]
Copy

TEDS underbody fault location algorithm in virtue of weak texture matching

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 3 Page number: 670-678 Column: 学术论文—智能系统 Public date: 2024-05-05
Title:
TEDS underbody fault location algorithm in virtue of weak texture matching
Author(s):
HUANG Yueyu;  ZHOU Hang;  CHEN Yehong;  LU Xin;  YU Jia;  HAN Ruiyu
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
Keywords:
image registration; feature matching; weak texture feature; potential fault; area location; topological crossover number; mean shift; feature selection
CLC:
TP391
DOI:
10.11992/tis.202303006
Abstract:
Fault recognition accuracy in the trouble of moving EMU detection system (TEDS) is suboptimal. Thus, a method for locating potential fault areas at the bottom of EMU by means of weak texture matching is proposed. First, a large number of feature points in the weak texture areas are detected using the topological crossover number. Second, feature points are selected on the basis of the topological crossover number of each pixel within a specified ring area centered on the feature points. This approach aims to construct corresponding feature vectors to achieve the matching of weak texture features. Finally, the registered image is compared to locate the potential fault areas. Experimental results show that the algorithm ensures matching accuracy; it can also detect most potential fault areas. The matching accuracy of weak texture areas is more than 80%, with feature matching pairs in all image pairs. Such a result provides favorable conditions for accurate fault classification in the future.
References:
[1] 刘洋. 关于提升TEDS故障预警准确率的研究[J]. 轨道交通装备与技术, 2019(3): 18–19
LIU Yang. Improving the accuracy of fault early warning for TEDS system[J]. Rail transportation equipment and technology, 2019(3): 18–19
[2] 刘彬. 动车组运行故障图像检测系统(TEDS)运用研究与思考[J]. 中国铁路, 2017(12): 61–65
LIU Bin. Research and thought on trouble of moving EMU detection system(TEDS)[J]. China railway, 2017(12): 61–65
[3] 陈伯施. 科技赋能轨道交通移动装备发展[J]. 铁道车辆, 2021, 59(1): 1–6
CHEN Boshi. Development of rail transit mobile equipment empowered by technology[J]. Rolling stock, 2021, 59(1): 1–6
[4] 杨凯. TEDS动车组故障图像数据库建立技术研究[J]. 铁道机车车辆, 2020, 40(6): 38–42,81
YANG Kai. TEDS EMU fault image database[J]. Railway locomotive & car, 2020, 40(6): 38–42,81
[5] 王锐. 浅谈动车组运行故障动态图像检测系统(TEDS)实践与故障应急处理办法[J]. 工业设计, 2015(8): 80–81
WANG Rui. Discussion on TEDS practice and fault emergency treatment methods[J]. Industrial design, 2015(8): 80–81
[6] 彭丹, 周航. 基于轨边图像SURF特征的动车底部件异常检测算法[J]. 信息系统工程, 2016(2): 127–128
PENG Dan, ZHOU Hang. Anomaly detection algorithm of moving car bottom parts based on SURF feature of rail edge image[J]. China CIO news, 2016(2): 127–128
[7] 彭丹. 基于轨边图像SURF特征的动车底部部件异常检测算法[D]. 北京: 北京交通大学, 2016.
PENG Dan. An abnormal detection algorithm of the EMU bottom based on the SURF features of the track-side image[D]. Beijing: Beijing Jiaotong University, 2016.
[8] BAY H, TUYTELAARS T, VAN GOOL L. SURF: speeded up robust features[M]//Computer Vision – ECCV 2006. Berlin: Springer Berlin Heidelberg, 2006: 404-417.
[9] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91–110.
[10] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: an efficient alternative to SIFT or SURF[C]//2011 International Conference on Computer Vision. Barcelona: IEEE, 2011: 2564-2571.
[11] ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection[M]//Computer Vision -ECCV 2006. Berlin: Springer Berlin Heidelberg, 2006: 430–443.
[12] CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF: binary robust independent elementary features[C]//European Conference on Computer Vision. Berlin: Springer, 2010: 778–792.
[13] 丁国绅, 乔延利, 易维宁, 等. 基于光谱图像空间的改进SIFT特征提取与匹配[J]. 北京理工大学学报, 2022, 42(2): 192–199
DING Guoshen, QIAO Yanli, YI Weining, et al. Improved SIFT feature extraction and matching based on spectral image space[J]. Transactions of Beijing institute of technology, 2022, 42(2): 192–199
[14] 胡旻涛, 彭勇, 徐赟. 基于改进SURF的快速图像配准算法[J]. 传感器与微系统, 2017, 36(11): 151–153
HU Mintao, PENG Yong, XU Yun. Fast image matching algorithm based on improved SURF[J]. Transducer and microsystem technologies, 2017, 36(11): 151–153
[15] WEI Yanhui, YANG Pengfei, XU Lixue, et al. An improved SURF algorithm based on gradient and amplitude pre-computation[C]//2019 IEEE International Conference on Mechatronics and Automation. Tianjin: IEEE, 2019: 456–462.
[16] HAN Leng, SUN Xia, WANG Jiawei, et al. Research on SURF feature matching algorithm based on lab color space[C]//2020 3rd International Conference on Robotics, Control and Automation Engineering. Chongqing: IEEE, 2020: 116–121.
[17] 洪鹏程, 唐垚, 任重. 基于SURF分割圆形区域的图像拼接[J]. 电讯技术, 2021, 61(11): 1424–1430
HONG Pengcheng, TANG Yao, REN Zhong. Image stitching based on SURF segmentation of circular regions[J]. Telecommunication engineering, 2021, 61(11): 1424–1430
[18] 张学峰, 马行, 穆春阳. 基于四叉树的SIFT与K-D树融合的图像匹配研究[J]. 电子测量技术, 2021, 44(22): 121–127
ZHANG Xuefeng, MA Xing, MU Chunyang. Research on image matching based on quadtree fusion of SIFT and K-D tree[J]. Electronic measurement technology, 2021, 44(22): 121–127
[19] WANG Shuoshi, LI Lin. Urban street image matching method based on improved SURF algorithm[C]//Proceedings of 2018 Chinese Intelligent Systems Conference. Singapore: Springer, 2019: 135–144.
[20] LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK: binary robust invariant scalable keypoints[C]//2011 International Conference on Computer Vision. Barcelona: IEEE, 2011: 2548–2555.
[21] 章盛, 李培华, 钱名思, 等. 融入曲率尺度空间算法的图像配准方法[J]. 激光与红外, 2021, 51(3): 379–387
ZHANG Sheng, LI Peihua, QIAN Mingsi, et al. Image registration method based on curvature scale space algorithm[J]. Laser & infrared, 2021, 51(3): 379–387
[22] RAMYA P P, AJAY J. Object recognition and classification based on improved bag of features using surf and mser local feature extraction[C]//2019 1st International Conference on Innovations in Information and Communication Technology. Chennai: IEEE, 2019: 1–4.
[23] 陈伟, 刘宇, 王亚伟, 等. 基于改进的FAST-SURF快速图像拼接算法[J]. 应用光学, 2021, 42(4): 636–642
CHEN Wei, LIU Yu, WANG Yawei, et al. Fast image stitching algorithm based on improved FAST-SURF[J]. Journal of applied optics, 2021, 42(4): 636–642
[24] 李国竣, 徐延海, 段杰文, 等. 利用局部自适应阈值方法提取ORB-SLAM特征点[J]. 测绘通报, 2021(9): 32–36,48
LI Guojun, XU Yanhai, DUAN Jiewen, et al. ORB-SLAM method based on local adaptive threshold extraction feature points[J]. Bulletin of surveying and mapping, 2021(9): 32–36,48
[25] 毛敏. 基于宽基线的弱纹理特征点提取与描述方法研究[D]. 上海: 东华大学, 2014.
MAO Min. Research on Point Detector and Descriptor for Textureless Object Surface Based on Wide Baseline Stereo[D]. Shanghai: Donghua University, 2014.
[26] 马东岭, 毛力波, 吴鼎辉, 等. 一种顾及纹理特征的自适应密集匹配方法[J]. 测绘科学, 2022, 47(2): 70–78,101
MA Dongling, MAO Libo, WU Dinghui, et al. An adaptive dense matching method considering texture features[J]. Science of surveying and mapping, 2022, 47(2): 70–78,101
[27] 程鹏飞, 周修庄, 唐玲, 等. 一种面向弱纹理图像的特征点描述子[J]. 北京邮电大学学报, 2021, 44(6): 13–19
CHENG Pengfei, ZHOU Xiuzhuang, TANG Ling, et al. A feature point descriptor for texture-less images[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(6): 13–19
[28] 章毓晋. 图像工程[M]. 4版. 北京: 清华大学出版社, 2018: 257-258.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems