A MSA-YOLO Obstacle Detection Algorithm for Rail Transit in Foggy Weather
Source abstract
Abstract
Obstacles on rail transit significantly compromise operational safety, particularly under dense fog conditions. To address missed and false detections in traditional rail transit detection methods, this paper proposes a multi-scale adaptive YOLO (MSA-YOLO) algorithm. The algorithm incorporates six filters: defog, white balance, gamma, contrast, tone, and sharpen, to remove fog and enhance image quality. However, determining the hyperparameters of these filters is challenging. We employ a multi-scale adaptive module to optimize filter hyperparameters, enhancing fog removal and image quality. Subsequently, YOLO is utilized to detect obstacles on rail transit tracks. The experimental results are encouraging, demonstrating the effectiveness of our proposed method in foggy scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Data Management and Algorithms · Maritime Navigation and Safety · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
Zhejiang Stream Rail Intelligent Control Technology Co., Ltd., Jiaxing 314001, China
School of Computer and Information Engineering, Institute for Artificial Intelligence, Shanghai Polytechnic University, Shanghai 201209, China
Shanghai Stream Rail Transportation Equipment Co., Ltd., Shanghai 200126, China
Funding
the Research Project of Jiaxing Civil Technology Innovation Research · Innovative Education Special Project for Intelligent Navigation Applications in 2023
References (33)
Show source-provided references
1. Urban rail transit obstacle detection based on improved R-CNN10.1016/j.measurement.2022.111277 ↗
2. Guo, J., Lou, H., Chen, H., Liu, H., Gu, J., Bi, L., and Duan, X. (2023). A new detection algorithm for alien intrusion on highway. Sci. Rep., 13.10.1038/s41598-023-37686-w ↗
3. Meng, C., Wang, Z., Shi, L., Gao, Y., Tao, Y., and Wei, L. (2023). SDRC-YOLO: A novel foreign object intrusion detection algorithm in railway scenarios. Electronics, 12.10.3390/electronics12051256 ↗
4. A railway intrusion detection method based on decomposition and semi-supervised learning for accident protection10.1016/j.aap.2023.107124 ↗
5. Arfi, A.M., Bal, D., Hasan, M.A., Islam, N., and Arafat, Y. (June, January ). Real time human face detection and recognition based on Haar features. Proceedings of the 2020 IEEE Region 10 Symposium, Dhaka, Bangladesh.10.1109/TENSYMP50017.2020.9230857 ↗
6. Object detection using template and HOG feature matching
7. Content-based image retrieval system using ORB and SIFT features10.1007/s00521-018-3677-9 ↗
8. Two-stage traffic sign detection and recognition based on SVM and convolutional neural networks10.1049/iet-ipr.2019.0634 ↗
9. Chen, L., Liu, Z., Tong, L., Jiang, Z., Wang, S., Dong, J., and Zhou, H. (2020, January 19–24). Underwater object detection using invert multi-class Adaboost with deep learning. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9207506 ↗
10. YOLO with adaptive frame control for real-time object detection applications10.1007/s11042-021-11480-0 ↗
11. Rail transit obstacle detection based on improved CNN
12. A stable lightweight and adaptive feature enhanced convolution neural network for efficient railway transit object detection10.1109/TITS.2022.3156267 ↗
13. Single image haze removal using dark channel prior
14. Sindagi, V.A., Oza, P., Yasarla, R., and Patel, V.M. (2020, January 13). Prior-based domain adaptive object detection for hazy and rainy conditions. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58568-6_45 ↗
15. Rodriguez, L.F., Uribe, J.A., and Bonilla, J.V. (2012, January 12–14). Obstacle detection over rails using hough transform. Proceedings of the 2012 XVII Symposium of Image, Signal Processing, and Artificial Vision (STSIVA), Medellin, Colombia.
16. Ye, H., Shang, G., Wang, L., and Zheng, M. (2015, January 14–16). A new method based on hough transform for quick line and circle detection. Proceedings of the 2015 8th International Conference on Biomedical Engineering and Informatics (BMEI), Shenyang, China.10.1109/BMEI.2015.7401472 ↗
17. Karaduman, M. (December, January 30). Image processing based obstacle detection with laser measurement in railways. Proceedings of the 2017 10th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey.
18. Mukojima, H., Deguchi, D., Kawanishi, Y., Ide, I., Murase, H., Ukai, M., Nagamine, N., and Nakasone, R. (2016, January 25–28). Moving camera background-subtraction for obstacle detection on railway tracks. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.10.1109/ICIP.2016.7533104 ↗
19. Yao, T., Dai, S., Wang, P., and He, Y. (2012, January 16–18). Image based obstacle detection for automatic train supervision. Proceedings of the 2012 5th International Congress on Image and Signal Processing, Chongqing, China.10.1109/CISP.2012.6469703 ↗
20. Wang, Z., Wu, X., Yan, Y., Jia, C., Cai, B., Huang, Z., Wang, G., and Zhang, T. (2015, January 14–16). An inverse projective mapping-based approach for robust rail track extraction. Proceedings of the 2015 8th International Congress on Image and Signal Processing (CISP), Shenyang, China.10.1109/CISP.2015.7408003 ↗
21. Ubbens, T.W., and Schuurman, D.C. (2009, January 3–6). Vision-based obstacle detection using a support vector machine. Proceedings of the 2009 Canadian Conference on Electrical and Computer Engineering, St. John’s, NL, Canada.10.1109/CCECE.2009.5090176 ↗
22. Sattiraju, R., Kochems, J., and Schotten, H.D. (June, January 31). Machine learning based obstacle detection for Automatic Train Pairing. Proceedings of the 2017 IEEE 13th International Workshop on Factory Communication Systems (WFCS), Trondheim, Norway.10.1109/WFCS.2017.7991962 ↗
23. Arvind, C.S., and Senthilnath, J. (2020, January 28). Autonomous vehicle for obstacle detection and avoidance using reinforcement learning. Proceedings of the Soft Computing for Problem Solving: SocProS 2018, Singapore.10.1007/978-981-15-0035-0_5 ↗
24. An intelligent railway surveillance framework based on recognition of object and railway track using deep learning10.1007/s11042-022-12059-z ↗
25. Pan, H., Li, Y., Wang, H., and Tian, X. (2022). Railway obstacle intrusion detection based on convolution neural network multitask learning. Electronics, 11.10.3390/electronics11172697 ↗
26. Efficient rail area detection using convolutional neural network10.1109/ACCESS.2018.2883704 ↗
27. Real-world railway traffic detection based on faster better network10.1109/ACCESS.2018.2879270 ↗
28. Automated detection of grade-crossing-trespassing near misses based on computer vision analysis of surveillance video data10.1016/j.ssci.2017.11.023 ↗
29. Exposure: A white-box photo post-processing framework
30. Image enhancement via adaptive unsharp masking10.1109/83.826787 ↗
31. Zheng, S., Wu, J., Duan, S., Liu, F., and Pan, J. (2022). An improved crowd counting method based on YOLOv3. Mob. Netw. Appl., 1–9.10.1007/s11036-022-02082-7 ↗
32. 3d object detection from images for autonomous driving: A survey
33. Liu, W., Ren, G., Yu, R., Guo, S., Zhu, J., and Zhang, L. (March, January 22). Image-adaptive YOLO for object detection in adverse weather conditions. Proceedings of the AAAI Conference on Artificial Intelligence, Online.