The skylight process represents a pivotal element of railway maintenance work; however, it encompasses substantial safety risks. The prompt identification of trespassing behaviors during the skylight process is crucial for maintaining railway stability and ensuring worker safety. Existing trespassing detection research is mainly based on railway operation scenes, with no prior studies focusing on trespassing detection in the context of the skylight process in railway maintenance. Addressing these challenges, this study proposes an algorithm for detecting trespassing by railway workers during the skylight process, utilizing the You Only Look Once instance segmentation model trained on the manually annotated data set with augmentation. This trespassing detection algorithm includes innovative elements, such as the horizontal line detection method, customized width ratio, and a customized rule for identifying the railway under maintenance. The proposed algorithm is designed to aid safety personnel at skylight process sites by providing enhanced supervision and effectively detecting instances of worker trespassing. With a detection precision exceeding 97% in the experimental results, this algorithm proved its efficiency in the railway skylight process, underscoring its extensive potential for diverse trespassing detection applications.
BouraimaM. B.QiuY.YusupovB.NdjegwesC. M.A Study on the Development Strategy of the Railway Transportation System in the West African Economic and Monetary Union (WAEMU) Based on the SWOT/AHP Technique. Scientific African, Vol. 8, 2020, p. e00388.
2.
LiuZ.LiuF.YaoS.ChenD.YangM.Research on Numerical Simulation of Transient Pressure for High-Speed Train Passing Through the Most Unfavourable Length Tunnel. Transportation Safety and Environment, Vol. 5, No. 3, 2023, p. tdac059.
3.
PappaterraM. J.PappaterraM. L.FlamminiF.A Study on the Application of Convolutional Neural Networks for the Maintenance of Railway Tracks. Discover Artificial Intelligence, Vol. 4, No. 1, 2024, p. 30.
4.
LuC.CaiC.Overview on Safety Management and Maintenance of High-Speed Railway in China. Transportation Geotechnics, Vol. 25, 2020, p. 100397.
5.
GrabušićS.BarićD.A Systematic Review of Railway Trespassing: Problems and Prevention Measures. Sustainability, Vol. 15, No. 18, 2023, p. 13878.
6.
WangX.LiuJ.KhattakA. J.ClarkeD.Non-Crossing Rail-Trespassing Crashes in the Past Decade: A Spatial Approach to Analyzing Injury Severity. Safety Science, Vol. 82, 2016, pp. 44–55.
7.
DalalN.TriggsB.Histograms of Oriented Gradients for Human Detection. Proc., IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, June20, 2005, Vol. 1, IEEE, New York, NY, pp. 886–893.
8.
OjalaT.PietikäinenM.HarwoodD.A Comparative Study of Texture Measures with Classification Based on Featured Distributions. Pattern Recognition, Vol. 29, No. 1, 1996, pp. 51–59.
9.
HeK.GkioxariG.DollárP.GirshickR.Mask R-CNN. Proc., IEEE International Conference on Computer Vision, IEEE, Honolulu, HI, 2017, pp. 2961–2969.
10.
RedmonJ.You Only Look Once: Unified, Real-Time Object Detection. Proc., IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, NV, 2016.
11.
RedmonJ.FarhadiA.YOLO9000: Better, Faster, Stronger. Proc., IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, HI, July2017, pp. 7263–7271.
12.
BochkovskiyA.WangC. Y.LiaoH. Y.Yolov4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934, 2020.
13.
GeZ.Yolox: Exceeding Yolo Series in 2021. arXiv preprint arXiv:2107.08430, 2021.
14.
WangC. Y.YehI. H.LiaoH. Y.You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv preprint arXiv:2105.04206, 2021.
15.
WangC. Y.BochkovskiyA.LiaoH. Y.YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proc., IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Vancouver, BC, Canada, 2023, pp. 7464–7475.
16.
GirshickR.Fast R-CNN. Proc., IEEE International Conference on Computer Vision, Piscataway, NJ, IEEE, New York, NY, Vol. 2, 2015, pp. 1440–1448.
17.
RenS.HeK.GirshickR.SunJ.Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 6, 2016, pp. 1137–1149.
18.
LiuS.JiaJ.FidlerS.UrtasunR.SGN: Sequential Grouping Networks for Instance Segmentation. Proc., IEEE International Conference on Computer Vision, IEEE, Venice, Italy, 2017, pp. 3496–3504.
19.
GaoN.ShanY.WangY.ZhaoX.YuY.YangM.HuangK.SSAP: Single-Shot Instance Segmentation with Affinity Pyramid. Proc., IEEE/CVF International Conference on Computer Vision, IEEE, Seoul, South Korea, 2019, pp. 642–651.
20.
WangX.ZhangR.ShenC.KongT.LiL.Solo: A Simple Framework for Instance Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, No. 11, 2021, pp. 8587–8601.
21.
WangX.ZhangR.KongT.LiL.ShenC.Solov2: Dynamic and Fast Instance Segmentation. Advances in Neural Information Processing Systems, Vol. 33, 2020, pp. 17721–1732.
22.
ZhangZ.ChenP.HuangY.DaiL.XuF.HuH.Railway Obstacle Intrusion Warning Mechanism Integrating YOLO-Based Detection and Risk Assessment. Journal of Industrial Information Integration, Vol. 38, 2024, p. 100571.
23.
ZhangZ.TrivediC.LiuX.Automated Detection of Grade-Crossing-Trespassing Near Misses Based on Computer Vision Analysis of Surveillance Video Data. Safety Science, Vol. 110, 2018, pp. 276–285.
24.
NiuH.HouT.Fast Detection Study of Foreign Object Intrusion on Railway Track. Archives of Transport, Vol. 47, No. 3, 2018, pp. 79–89.
25.
KetchamM.GanokratanaaT.SrinhichaarnunS.The Intruder Detection System for Rapid Transit Using CCTV Surveillance Based on Histogram Shapes. Proc., 11th International Joint Conference on Computer Science and Software Engineering (JCSSE), Chon Buri, Thailand, May14, 2014, IEEE, New York, NY, pp. 1–6.
26.
ZamanA.RenB.LiuX.Artificial Intelligence-Aided Automated Detection of Railroad Trespassing. Transportation Research Record: Journal of the Transportation Research Board. 2019. 2673: 25–37.
27.
ZhangZ.ZamanA.XuJ.LiuX.Artificial Intelligence-Aided Railroad Trespassing Detection and Data Analytics: Methodology and a Case Study. Accident Analysis & Prevention, Vol. 168, 2022, p. 106594.
28.
PratamaR. P.SupangkatS. H.Trespassing Detection System on a Smart Video Surveillance System for Level Crossing. Proc., 10th International Conference on ICT for Smart Society (ICISS), Bandung, Indonesia, September 6, 2023, IEEE, New York, NY, pp. 1–4.
29.
YangX.LiJ. Q.YangG.LiuW.WangK.A Deep Learning Approach for Automated Detection of Railroad Trespassers. Proc., International Conference on Transportation and Development, American Society of Civil Engineers, Seattle, Wasington, 2022, pp. 177–188.
30.
LinT. Y.MaireM.BelongieS.HaysJ.PeronaP.RamananD.DollárP.ZitnickC. L.Microsoft COCO: Common Objects in Context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V (FleetD.PajdlaT.SchieleB.TuytelaarsT., eds.). Springer International Publishing, Cham, 2014, pp. 740–755.
31.
MaharanaK.MondalS.NemadeB.A Review: Data Pre-Processing and Data Augmentation Techniques. Global Transitions Proceedings, Vol. 3, No. 1, 2022, pp. 91–99.
32.
KhoslaC.SainiB. S.Enhancing Performance of Deep Learning Models with Different Data Augmentation Techniques: A Survey. Proc., International Conference on Intelligent Engineering and Management (ICIEM), London, IEEE, New York, NY, 2020, pp. 79–85.
33.
ChlapP.MinH.VandenbergN.DowlingJ.HollowayL.HaworthA.A Review of Medical Image Data Augmentation Techniques for Deep Learning Applications. Journal of Medical Imaging and Radiation Oncology, Vol. 65, No. 5, 2021, pp. 545–563.
34.
RussellB. C.TorralbaA.MurphyK. P.FreemanW. T.LabelMe: A Database and Web-Based Tool for Image Annotation. International Journal of Computer Vision, Vol. 77, 2008, pp. 157–173.
35.
RanjithA.VijayaragavanS. P.NirmalraniV.MuthukumaranN.An IoT based Monitoring System to Detect Animal in the Railway Track using Deep Learning Neural Network. Proc., 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, August 17, 2022, IEEE, New York, NY, pp. 1246–1253.
36.
DrutaC.AldenA. S.Preventing Animal-Vehicle Crashes Using a Smart Detection Technology and Warning System. Transportation Research Record: Journal of the Transportation Research Board, 2020. 2674: 680–689.
37.
HeX.ZengD.Real-Time Pedestrian Warning System on Highway Using Deep Learning Methods. Proc., International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Xiamen, China, November 6, 2017, IEEE, New York, NY, pp. 701–706.
38.
ChenC.QinH.BaiY.Exploration of Vision-Based Railway Turnout Recognition and Application. Proc., International Conference on Development and Application Systems (DAS), Suceava, Romania, May 23, 2024, IEEE, New York, NY, pp. 127–135.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
