KCF-Hash-Match Target Tracking Algorithm for Identifying Wheel Lateral Sway of High-speed Train

doi:10.3901/JME.2023.24.223

Abstract

Abstract: A good wheel-rail contact state is an important guarantee for the running safety of high-speed trains. The relative lateral movement of wheel and rail is an important indicator for judging the wheel-rail contact state, which directly determines the danger of wheel derailment. The wheel-rail online tracking monitoring technology based on machine vision can provide a new idea for the state identification of the wheel-rail contact point of high-speed trains. The test adopts the method of installing a camera at the bottom of the bogie to obtain images of wheel rail contact during high-speed train operation. Considering the advantages of fast tracking speed of the KCF algorithm and the high tracking accuracy of the template matching algorithm, and incorporating the principle of hashing algorithm, a Kernel Correlation Filtering-Hash-Match algorithm(KCF-Hash-Match)that can automatically identify wheel-rail contact geometry is proposed, which is applied to the monitoring of abnormal wheel lateral sway of high-speed trains under complex condition. The results show that the KCF-Hash-Match algorithm can solve the error accumulation problem existing in the traditional KCF algorithm when deal with tracking fast moving targets. When the allowable error threshold is 8 pixels, the accuracy rate can attain 99.8%. Compared with the field measured data, the KCF-Hash-Match algorithm has high tracking accuracy and can realize the safety monitoring of high-speed train wheel lateral sway behavior.

Key words: high-speed train, wheel lateral sway, kernel correlation filtering, hash algorithm, template matching

CLC Number:

U270

LU Wanchun, JIANG Peibin, LING Liang, WANG Kaiyun, ZHAI Wanming, DING Xin. KCF-Hash-Match Target Tracking Algorithm for Identifying Wheel Lateral Sway of High-speed Train[J]. Journal of Mechanical Engineering, 2023, 59(24): 223-230.

References

[1] 金学松,赵国堂,梁树林,等. 高速铁路轮轨磨损特征、机理、影响和对策-车轮踏面横向磨耗[J]. 机械工程学报,2018,54(4):3-13. JIN Xuesong,ZHAO Guotang,LIANG Shulin,et al. Characteristics,mechanisms,influences and counter measures of high speed wheel/rail wear:Transverse wear of wheel tread[J]. Journal of Mechanical Engineering,2018,54(4):3-13.
[2] 金学松,吴越,梁树林,等. 高速列车车轮多边形磨耗、机理、影响和对策分析[J]. 机械工程学报,2020,56(16):118-136. JIN Xuesong,WU Yue,LIANG Shulin,et al. Characteristics,mechanism,influences and countermeasures of polygonal wear of high-speed train wheels[J]. Journal of Mechanical Engineering,2020,56(16):118-136.
[3] 肖新标. 复杂环境状态下高速列车脱轨机理研究[D]. 成都:西南交通大学,2013. XIAO Xinbiao. Study on high-speed train derailment mechanism in severe environment[D]. Chengdu:Southwest Jiaotong University,2013.
[4] STRATMAN B,LIU Y M,MAHADEVAN S. Structural health monitoring of railroad wheels using wheel impact load detectors[J]. Journal of Failure Analysis and Prevention,2007,7(3):218-225.
[5] GOMEZ E,GIMÉNEZ J G,ALONSO A. Method for the reduction of measurement errors associated to the wheel rotation in railway dynamometric wheelsets[J]. Mechanical Systems and Signal Processing,2011,25(8):3062-3077.
[6] 宫雪,任尊松,范童柏,等. 轮轨力连续测试方法及1:5试验台验证[J]. 机械工程学报,2020,56(2):184-191. GONG Xue,REN Zunsong,FAN Tongbai,et al. Research on continuous measurement method for wheel-rail forces and validation with 1:5 scale roller rig test[J]. Journal of Mechanical Engineering,2020,56(2):184-191.
[7] 杨桐. 基于图像处理的列车轮轨接触关系研究[D]. 兰州:兰州交通大学,2020. YANG Tong. Research on train-rail contact relationship based on image processing[D]. Lanzhou:Lanzhou Jiaotong University,2020.
[8] 马增强,王永胜,宋子彬. 基于激光源的机车轮轨相对横移图像检测[J]. 图学学报,2017,38(4):623-628. MA Zengqiang,WANG Yongsheng,SONG Zibin. The image detection of wheel-rail relative lateral displacement based on laser[J]. Journal of Graphics,2017,38(4):623-628.
[9] SHI D C,ŠABANOVIČ E,RIZZETTO L,et al. Deep learning based virtual point tracking for real-time target-less dynamic displacement measurement in railway applications[J]. Mechanical Systems and Signal Processing,2022,166:108482.
[10] 孟琭,杨旭. 目标跟踪算法综述[J]. 自动化学报,2019,45(7):1244-1260. MENG Lu,YANG Xu. A survey of object tracking algorithms[J]. Acta Automatica Sinica,2019,45(7):1244-1260.
[11] PEI L L,ZHANG H,YANG B. Improved Camshift object tracking algorithm in occluded scenes based on AKAZE and Kalman[J]. Multimedia Tools and Applications,2022,81(2):2145-2159.
[12] DAI Y T,CHEN Z G,FU Y. Rotation-based scale adaptive moving target tracking algorithm[J]. Laser & Optoelectronics Progress,2021,58(12):1210019.
[13] HENRIQUES J F,CASEIRO R,MARTINS P,et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(3):583-596.
[14] LIANG H G,GAO D M,LI J W,et al. Improved target tracking algorithm based on kernelized correlation filter[J]. Journal of Electronic Imaging,2019,28(2):021008.
[15] 成旺荣. 基于KCF的抗云遮挡目标跟踪方法研究[D]. 武汉:华中科技大学,2020. CHENG Wangrong. Research on target tracking algorithm against cloud occlusion based on KCF[D]. Wuhan:Huazhong University of Science and Technology,2020.
[16] HADMI A,ROUIJEL A. A novel approach for robust perceptual image hashing[J]. Computer and Information Science,2021,14(3):1-38.
[17] 董晶. 模板图像快速可靠匹配技术研究[D]. 长沙:国防科学技术大学,2015. DONG Jing. Study on fast and reliable pattern match[D]. Changsha:National University of Defense Technology,2015.
[18] CATERINA G D,SORAGHAN J J. Robustcomplete occlusion handling in adaptive template matching target tracking[J]. Electronics Letters,2012,48(14):831-832.