Tao Hou1, Yannan Chen This email address is being protected from spambots. You need JavaScript enabled to view it.1, Caiwen Bao1, and Yuhu Chen1

1School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China


 

Received: May 14, 2021
Accepted: July 29, 2021
Publication Date: September 15, 2021

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.


Download Citation: ||https://doi.org/10.6180/jase.202204_25(2).0015  


ABSTRACT


Aiming at problems such as the untrustworthy association between spatial regularization weight and intrusive foreign object in complex railway scenes, as well as the degradation of correlation filter model, fully excavate the expressive ability of deep space features, and a foreign object tracking algorithm based on correlation filtering with depth space and time perception regularization is put forward. Firstly, selecte the fifth-level convolution feature of the Visual Geometry Group (VGG) network to extract the spatial area information of the foreign object, which is used to solve the regularization guide weight.
Secondly, a regularization term based on depth space is added to the objective function, whose aim is to establish a more reliable association between the spatial regularization weight and the invading foreign object. Thirdly, the time perception term is added to establish the connection between the filters in time. Finally, based on the depth space, a simple and effective model update strategy is proposed. On the public OBT datasets and complex railway scenes, the tracking results of the algorithm in this paper and the existing multiple algorithms are compared and analyzed. The results show that in complex railway scenes, the algorithm in this paper is superior to other algorithms in distance accuracy and success rate. The tracking spe ed is 23.1FPS, which basically meets the real-time requirements. Therefore, the correlation filtering algorithm of the improved regularization model is of great significance to railway safety.


Keywords: railway foreign object tracking; correlation filtering; depth space; time perception; spatial regularization; model update


REFERENCES


  1. [1] Y.Wang. “Gaosu tielu changjing fenge yu shibie suanfa yanjiu [Research on high-speed railway scene segmentation and recognition algorithm]". (phdthesis). Beijing, China, 2019.
  2. [2] X. Li, L. Zhu, and Z. Yu, (2020) “Zishiying tielu changjing qianjing mubiao jiance [Adaptive railway scene foreground target detection]" Jiaotong yunshu xitong gongcheng yu xinxi v.20(02): 87–94.
  3. [3] T. Hou, H. Wu, and H. Niu, (2020) “Gaijin MOGLRMF de tiegui dongtai yiwu jiance [Real-time detection of rail dynamic foreign object intrusion based on improved MOG-LRMF]" Jiaotong yunshu xitong gongcheng yu xinxi (2): 91–100.
  4. [4] H. Shi, H. Chai, Y.Wang, and Z. Yu, (2015) “Jiyu mubiao shibie yu genzong de qianrushi tielu yiwu qinxian jiance suanfa yanjiu [Research on Embedded Railway Foreign Body Intrusion Detection Algorithm Based on Target Recognition and Tracking]" Tiedao xuebao 37(7): 58–65.
  5. [5] Z. Qu, R. Zhou, X. Sun, S. Yuan, and L. Zou, (2019) “Chidu zishiying de tielu yiwu qinxian PSA-Kcf jiangwei genzong fangfa [Scale adaptive PSA-Kcf dimension reduction tracking method foreign body intrusion]" Tiedao xuebao 041(005): 71–81.
  6. [6] H. Wu. “Tielu guidao yiwu ruqin de zhineng shibie ji zidong yujing yanjiu [Research on intelligent recognition and automatic early warning of foreign object intrusion on railway track]". (phdthesis). Lanzhou, China., 2020.
  7. [7] R. Zhou. “Jiyu jiqi shijue de tielu yiwu qinxian lubangxing jiance ji genzong fangfa yanjiu [Research on Robustness Detection and Tracking Method of Railway Foreign Body Intrusion Limit Based on Machine Vision]". (phdthesis). Nanchang, China.
  8. [8] C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. “Hierarchical convolutional features for visual tracking”. In: Proceedings of the IEEE international conference on computer vision. 2015, 3074–3082.
  9. [9] J. Dai and N. Yan. “Robust Single-object Visual Tracking Framework via Fully Convolutional Siamese Network with Correlation Filter”. In: 2020 13th International Symposium on Computational Intelligence and Design (ISCID). IEEE. 2020, 359–363.
  10. [10] H. Fu, Y. Zhang, W. Zhou, X. Wang, and H. Zhang, (2020) “Learning reliable-spatial and spatial-variation regularization correlation filters for visual tracking" Image and Vision Computing 94: 103869.
  11. [11] K. Dai, D. Wang, H. Lu, C. Sun, and J. Li. “Visual tracking via adaptive spatially-regularized correlation filters”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 4670–4679.
  12. [12] D. Elayaperumal and Y. H. Joo, (2020) “Visual object tracking using sparse context-aware spatio-temporal correlation filter" Journal of Visual Communication and Image Representation 70: 102820.
  13. [13] X.-S. Wei, J.-H. Luo, J. Wu, and Z.-H. Zhou, (2017) “Selective convolutional descriptor aggregation for finegrained image retrieval" IEEE Transactions on Image Processing 26(6): 2868–2881.
  14. [14] Y.Wu, J. Lim, and M.-H. Yang. “Online object tracking: A benchmark”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2013, 2411–2418.
  15. [15] Y. Wu, J. Lim, and M.-H. Yang. “Object tracking benchmark”. In: Proceedings of the IEEE Transactions on Pattern Anaiysis and Machine Intelligence. 2015, 1834–1848.
  16. [16] M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. “Adaptive decontamination of the training set: A unified formulation for discriminative visual tracking”. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1430–1438.
  17. [17] M. Danelljan, A. Robinson, F. S. Khan, and M. Felsberg. “Beyond correlation filters: Learning continuous convolution operators for visual tracking”. In: European conference on computer vision. Springer. 2016, 472–488.
  18. [18] Y. Qi, S. Zhang, L. Qin, H. Yao, Q. Huang, J. Lim, and M.-H. Yang. “Hedged deep tracking”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, 4303–4311.
  19. [19] L. Bertinetto, J. Valmadre, J. F. Henriques, A. Vedaldi, and P. H. Torr. “Fully-convolutional siamese networks for object tracking”. In: European conference on computer vision. Springer. 2016, 850–865.
  20. [20] M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. “Convolutional features for correlation filter based visual tracking”. In: Proceedings of the IEEE international conference on computer vision workshops. 2015, 58–66.
  21. [21] A. Vedaldi and K. Lenc. “Matconvnet: Convolutional neural networks for matlab”. In: Proceedings of the 23rd ACM international conference on Multimedia. 2015, 689–692.


    
 

0.7
2020CiteScore
 
 
33rd percentile
Powered by  Scopus

SCImago Journal & Country Rank

Enter your name and email below to receive latest published articles in Journal of Applied Science and Engineering.