{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T10:13:09Z","timestamp":1791972789909,"version":"4.3.4"},"reference-count":37,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Amid rapid advancements in artificial intelligence, the detection of abnormal human behaviors in complex traffic environments has garnered significant attention. However, detection errors frequently occur due to interference from complex backgrounds, small targets, and other factors. Therefore, this paper proposes a research methodology that integrates the anomaly detection YOLO-SGCF algorithm with the tracking BoT-SORT-ReID algorithm. The detection module uses YOLOv8 as the baseline model, incorporating Swin Transformer to enhance global feature modeling capabilities in complex scenes. CBAM and CA attention are embedded into the Neck and backbone, respectively: CBAM enables dual-dimensional channel-spatial weighting, while CA precisely captures object location features by encoding coordinate information. The Neck layer incorporates GSConv convolutional modules to reduce computational load while expanding feature receptive fields. The loss function is replaced with Focal-EIoU to address sample imbalance issues and precisely optimize bounding box regression. For tracking, to enhance long-term tracking stability, ReID feature distances are incorporated during the BoT-SORT data association phase. This integrates behavioral category information from YOLO-SGCF, enabling the identification and tracking of abnormal pedestrian behaviors in complex environments. Evaluations on our self-built dataset (covering four abnormal behaviors: Climb, Fall, Fight, Phone) show mAP@50%, precision, and recall reaching 92.2%, 90.75%, and 86.57% respectively\u2014improvements of 3.4%, 4.4%, and 6% over the original model\u2014while maintaining an inference speed of 328.49 FPS. Additionally, generalization testing on the UCSD Ped1 dataset (covering six abnormal behaviors: Biker, Skater, Car, Wheelchair, Lawn, Runner) yielded an mAP score of 92.7%, representing a 1.5% improvement over the original model and outperforming existing mainstream models. Furthermore, the tracking algorithm achieved an MOTA of 90.8% and an MOTP of 92.6%, with a 47.6% reduction in IDS, demonstrating superior tracking performance compared to existing mainstream algorithms.<\/jats:p>","DOI":"10.3390\/s26020400","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T09:01:29Z","timestamp":1767862889000},"page":"400","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Fusion Algorithm for Pedestrian Anomaly Detection and Tracking on Urban Roads Based on Multi-Module Collaboration and Cross-Frame Matching Optimization"],"prefix":"10.3390","volume":"26","author":[{"given":"Wei","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7605-916X","authenticated-orcid":false,"given":"Xin","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanlan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luoyang","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Luo, X., Liu, Y., Hao, Y., and Du, H. (2024, January 22\u201324). A Study on Video Anomalous Behavior Recognition Based on Two-Stream Network. Proceedings of the 2024 6th International Conference on Natural Language Processing (ICNLP), Xi\u2019an, China.","DOI":"10.1109\/ICNLP60986.2024.10692970"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1007\/s40747-024-01743-2","article-title":"Advancing skeleton-based human behavior recognition: Multi-stream fusion spatiotemporal graph convolutional networks","volume":"11","author":"Liu","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isatra.2022.06.025","article-title":"SWSCAV: Real-time traffic management using connected autonomous vehicles","volume":"132","author":"Gokasar","year":"2023","journal-title":"ISA Trans."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"128102","DOI":"10.1016\/j.neucom.2024.128102","article-title":"Development and challenges of object detection: A survey","volume":"598","author":"Li","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zaharescu, A., and Wildes, R. (2010, January 5\u201311). Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event-driven processing. Proceedings of the European Conference on Computer Vision, Heraklion, Greece.","DOI":"10.1007\/978-3-642-15549-9_41"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tan, H., Zhai, Y., Liu, Y., and Zhang, M. (2016, January 20\u201325). Fast anomaly detection in traffic surveillance video based on robust sparse optical flow. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.","DOI":"10.1109\/ICASSP.2016.7472022"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhao, B., Fei-Fei, L., and Xing, E.P. (2011, January 20\u201325). Online detection of unusual events in videos via dynamic sparse coding. Proceedings of the CVPR 2011, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995524"},{"key":"ref_8","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.ijleo.2017.09.104","article-title":"Pedestrian abnormal event detection based on multi-feature fusion in traffic video","volume":"154","author":"Wang","year":"2018","journal-title":"Optik"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hsu, S.C., Chuang, C.H., Huang, C.L., Teng, R., and Lin, M.J. (2018, January 7\u20139). A video-based abnormal human behavior detection for psychiatric patient monitoring. Proceedings of the 2018 International Workshop on Advanced Image Technology (IWAIT), Chiang Mai, Thailand.","DOI":"10.1109\/IWAIT.2018.8369749"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 13\u201316). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_13","first-page":"1137","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 21\u201330). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Mehmood, A. (2021). Abnormal behavior detection in uncrowded videos with two-stream 3D convolutional neural networks. Appl. Sci., 11.","DOI":"10.3390\/app11083523"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Pathak, V., Diwakar, M., Roka, S., Pandey, N.K., and Mishra, A.K. (2025, January 17\u201318). Deep Learning for Anomaly Detection: A CNN-LSTM Autoencoder Approach. Proceedings of the 2025 3rd International Conference on Advancement in Computation & Computer Technologies (InCACCT), Gharuan, India.","DOI":"10.1109\/InCACCT65424.2025.11011326"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rohini, P.S., and Sowmy, I. (2025). Improved bounding box segmentation technique for crowd anomaly detection with optimal trained convolutional neural network. Netw. Comput. Neural Syst., 1\u201354.","DOI":"10.1080\/0954898X.2025.2475070"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I 14.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2860","DOI":"10.1109\/LSP.2024.3469787","article-title":"General optimization methods for YOLO series object detection in remote sensing images","volume":"31","author":"Nan","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ji, H., Zeng, X., Li, H., Ding, W., Nie, X., Zhang, Y., and Xiao, Z. (2020, January 10\u201312). Human abnormal behavior detection method based on T-TINY-YOLO. Proceedings of the 5th International Conference on Multimedia and Image Processing, Nanjing, China.","DOI":"10.1145\/3381271.3381273"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Xu, T., Chen, J., Li, Z., and Cai, Y. (2022, January 18\u201320). Escalator passenger posture anomaly detection based on improved SSD model. Proceedings of the 2022 12th International Conference on Information Technology in Medicine and Education (ITME), Xiamen, China.","DOI":"10.1109\/ITME56794.2022.00066"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Fang, M., Chen, Z., Przystupa, K., Li, T., Majka, M., and Kochan, O. (2021). Examination of abnormal behavior detection based on improved YOLOv3. Electronics, 10.","DOI":"10.3390\/electronics10020197"},{"key":"ref_23","first-page":"159","article-title":"Improved DETR for Crowded Pedestrian Detection","volume":"59","author":"Fan","year":"2023","journal-title":"J. Comput. Eng. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5681","DOI":"10.11591\/ijece.v14i5.pp5681-5690","article-title":"A cost-effective, reliable and accurate framework for multiple-target tracking by detection approach using deep neural network","volume":"14","author":"Seebaiah","year":"2024","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref_25","unstructured":"Parate, M.R., Bhurchandi, K.M., and Kothari, A.G. (2021). Anomaly detection in residential video surveillance on edge devices in iot framework. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, W., Ren, C., and Tan, A. (2024). Study on Nighttime Pedestrian Trajectory-Tracking from the Perspective of Driving Blind Spots. Electronics, 13.","DOI":"10.3390\/electronics13173460"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5513","DOI":"10.1007\/s40747-024-01426-y","article-title":"SCGTracker: Object feature embedding enhancement based on graph attention networks for multi-object tracking","volume":"10","author":"Feng","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Roka, S., and Diwakar, M. (2023, January 26\u201328). DCT: A lightweight approach for the real-time video anomaly detection in multi camera. Proceedings of the 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India.","DOI":"10.1109\/ICSCCC58608.2023.10176979"},{"key":"ref_29","unstructured":"Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18\u201324). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 14\u201319). Ghostnet: More features from cheap operations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 19\u201325). Coordinate attention for efficient mobile network design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e37072","DOI":"10.1016\/j.heliyon.2024.e37072","article-title":"Foreign object detection in urban rail transit based on deep differentiation segmentation neural network","volume":"10","author":"Tan","year":"2024","journal-title":"Heliyon"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_36","unstructured":"Aharon, N., Orfaig, R., and Bobrovsky, B.Z. (2022). BoT-SORT: Robust associations multi-pedestrian tracking. arXiv."},{"key":"ref_37","first-page":"101","article-title":"Anomalous behavior detection method of YOLOv8 improved by multi-scale fusion and FMB","volume":"60","author":"Shi","year":"2024","journal-title":"Comput. Eng. Appl."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/400\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T09:06:02Z","timestamp":1767863162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020400"],"URL":"https:\/\/doi.org\/10.3390\/s26020400","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]}}}