{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:13:38Z","timestamp":1791393218304,"version":"4.3.3"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Doctoral Academic Development Support Project of Tibet University","award":["zdbs202327"],"award-info":[{"award-number":["zdbs202327"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Traditional fall detection methods face significant limitations in complex environments, particularly under occlusion and poor lighting conditions. To address these challenges and enhance the detection accuracy in intelligent real-time monitoring systems, this study proposes an optimized BMR-YOLO framework based on the YOLOv8n architecture. Our approach introduces four strategic improvements to effectively overcome environmental constraints. First, we enhance the backbone network by incorporating a BiFormer vision transformer with dual-layer routing attention, enabling dynamic allocation of computational resources, while improving both computational efficiency and feature extraction performance. Next, we replace the C2f module in the backbone with C2f_rvb, enhancing the model\u2019s ability to handle multi-scale features while reducing computational requirements. Furthermore, we strengthen the detection head by adding the MultiSEAM attention mechanism, significantly improving the detection accuracy of occluded objects. Finally, we optimize the regression process by replacing the traditional CIoU loss with a direction-aware SIoU metric, thereby improving both the localization accuracy and training stability of bounding box regression. To validate our method, we constructed a comprehensive dataset, BMR-fall, containing over 10,000 annotated images that capture various fall scenarios, and performed cross-validation using the UR fall detection dataset. Experimental results demonstrate that BMR-YOLO achieves a notable improvement in mAP@0.5, rising from 0.852 to 0.899 on our proprietary dataset, while maintaining a low computational cost of 6.5 GFLOPs. Comparative analysis with existing methods shows that BMR-YOLO outperforms them under occlusion and lighting variation conditions, confirming the model\u2019s robustness and practical applicability for real-world deployment.<\/jats:p>","DOI":"10.1371\/journal.pone.0335992","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:30:54Z","timestamp":1762540254000},"page":"e0335992","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["BMR-YOLO: A deep learning approach for fall detection in complex environments"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4821-1646","authenticated-orcid":true,"given":"Hang","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4245-4010","authenticated-orcid":true,"given":"Ping","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"pone.0335992.ref001","unstructured":"Fast P. R-cnn. In: Digital TV, Wireless Multimedia Communication: 14th International Forum and IFTC 2017, Shanghai, China, November 8-9, 2017, Revised Selected Papers. Springer; 2018. p. 172."},{"key":"pone.0335992.ref002","doi-asserted-by":"crossref","unstructured":"Girshick R. Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. 2015. p. 1440\u20138.","DOI":"10.1109\/ICCV.2015.169"},{"key":"pone.0335992.ref003","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R. Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. p. 2961\u20139.","DOI":"10.1109\/ICCV.2017.322"},{"key":"pone.0335992.ref004","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY. SSD: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016 : 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I. 2016. p. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"pone.0335992.ref005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2020.3040485","article-title":"RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection","volume":"70","author":"X Cheng","year":"2021","journal-title":"IEEE Trans Instrum Meas."},{"key":"pone.0335992.ref006","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","article-title":"A review of yolo algorithm developments","volume":"199","author":"P Jiang","year":"2022","journal-title":"Procedia Computer Science."},{"key":"pone.0335992.ref007","unstructured":"Long KZ, Haron H, Ibrahim M, Eri ZD. An image-based fall detection system using you only look once (yolo) algorithm to monitor elders\u2019 fall events. In: Knowledge Management International Conference (KMICe). 2021."},{"issue":"8","key":"pone.0335992.ref008","doi-asserted-by":"crossref","first-page":"818","DOI":"10.3390\/machines11080818","article-title":"High-performance lightweight fall detection with an improved YOLOv5s algorithm","volume":"11","author":"Y Wang","year":"2023","journal-title":"Machines."},{"key":"pone.0335992.ref009","doi-asserted-by":"crossref","unstructured":"Raza A, Yousaf MH, Velastin SA. Human fall detection using YOLO: a real-time and AI-on-the-edge perspective. In: 2022 12th International Conference on Pattern Recognition Systems (ICPRS). 2022. p. 1\u20136. https:\/\/doi.org\/10.1109\/icprs54038.2022.9854070","DOI":"10.1109\/ICPRS54038.2022.9854070"},{"key":"pone.0335992.ref010","doi-asserted-by":"crossref","unstructured":"Chen Y, Du R, Luo K, Xiao Y. Fall detection system based on real-time pose estimation and SVM. In: 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE). 2021. p. 990\u20133.","DOI":"10.1109\/ICBAIE52039.2021.9390068"},{"key":"pone.0335992.ref011","doi-asserted-by":"crossref","unstructured":"Ros D, Dai R. A flexible fall detection framework based on object detection and motion analysis. In: 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2023. p. 63\u20138. https:\/\/doi.org\/10.1109\/icaiic57133.2023.10066990","DOI":"10.1109\/ICAIIC57133.2023.10066990"},{"key":"pone.0335992.ref012","doi-asserted-by":"crossref","unstructured":"Chen G, Sun S, Sun Y, Chen H, Zhang W, Su X. CAGn: high-order coordinated attention module for improving fall detection models. In: IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society. 2023. p. 1\u20136. https:\/\/doi.org\/10.1109\/iecon51785.2023.10311741","DOI":"10.1109\/IECON51785.2023.10311741"},{"key":"pone.0335992.ref013","doi-asserted-by":"crossref","unstructured":"Li X, Bao Y. Small target detection algorithm for UAV aerial photography based on improved YOLO V8n. In: 2024 6th International Conference on Data-driven Optimization of Complex Systems (DOCS). 2024. p. 870\u20135. https:\/\/doi.org\/10.1109\/docs63458.2024.10704374","DOI":"10.1109\/DOCS63458.2024.10704374"},{"key":"pone.0335992.ref014","doi-asserted-by":"crossref","unstructured":"Lin Z, Chen D, Zeng Y. Occlusion target detection based on improved YOLOv5 model. In: 2022 China Automation Congress (CAC). IEEE; 2022. p. 3014\u20139.","DOI":"10.1109\/CAC57257.2022.10055351"},{"key":"pone.0335992.ref015","doi-asserted-by":"crossref","unstructured":"Zhu L, Wang X, Ke Z, Zhang W, Lau R. BiFormer: vision transformer with bi-level routing attention. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. p. 10323\u201333. https:\/\/doi.org\/10.1109\/cvpr52729.2023.00995","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"pone.0335992.ref016","doi-asserted-by":"crossref","first-page":"110714","DOI":"10.1016\/j.patcog.2024.110714","article-title":"YOLO-FaceV2: a scale and occlusion aware face detector","volume":"155","author":"Z Yu","year":"2024","journal-title":"Pattern Recognition."},{"issue":"07","key":"pone.0335992.ref017","doi-asserted-by":"crossref","first-page":"12993","DOI":"10.1609\/aaai.v34i07.6999","article-title":"Distance-IoU loss: faster and better learning for bounding box regression","volume":"34","author":"Z Zheng","year":"2020","journal-title":"AAAI."},{"key":"pone.0335992.ref018","article-title":"SioU loss: more powerful learning for bounding box regression","author":"Z Gevorgyan","year":"2022","journal-title":"arXiv preprint"},{"key":"pone.0335992.ref019","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2018. p. 7132\u201341.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0335992.ref020","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS. Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV). 2018. p. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"pone.0335992.ref021","unstructured":"Liu Y, Shao Z, Hoffmann N. Global attention mechanism: retain information to enhance channel-spatial interactions. arXiv preprint 2021. https:\/\/doi.org\/arXiv:211205561"},{"key":"pone.0335992.ref022","article-title":"YOLOv6: a single-stage object detection framework for industrial applications","author":"C Li","year":"2022","journal-title":"arXiv preprint"},{"key":"pone.0335992.ref023","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. p. 7464\u201375. https:\/\/doi.org\/10.1109\/cvpr52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"pone.0335992.ref024","doi-asserted-by":"crossref","unstructured":"Chollet F. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 1251\u20138.","DOI":"10.1109\/CVPR.2017.195"},{"key":"pone.0335992.ref025","doi-asserted-by":"crossref","unstructured":"Li J, He F, Zhang L, Du B, Tao D. Progressive reconstruction of visual structure for image inpainting. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2019. p. 5962\u201371.","DOI":"10.1109\/ICCV.2019.00606"},{"key":"pone.0335992.ref026","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies. 2019. p. 4171\u201386."},{"key":"pone.0335992.ref027","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Liao HY. Yolov9: Learning what you want to learn using programmable gradient information. In: European conference on computer vision. 2024. p. 1\u201321.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"pone.0335992.ref028","first-page":"107984","article-title":"Yolov10: real-time end-to-end object detection","volume":"37","author":"A Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems."},{"key":"pone.0335992.ref029","unstructured":"Yang L, Zhang RY, Li L, Xie X. Simam: a simple, parameter-free attention module for convolutional neural networks. In: International conference on machine learning. PMLR; 2021. p. 11863\u201374."},{"key":"pone.0335992.ref030","doi-asserted-by":"crossref","unstructured":"Misra D, Nalamada T, Arasanipalai AU, Hou Q. Rotate to attend: convolutional triplet attention module. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 2021. p. 3139\u201348.","DOI":"10.1109\/WACV48630.2021.00318"},{"issue":"1","key":"pone.0335992.ref031","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TNN.2007.901277","article-title":"MPCA: multilinear principal component analysis of tensor objects","volume":"19","author":"H Lu","year":"2008","journal-title":"IEEE Trans Neural Netw."},{"key":"pone.0335992.ref032","doi-asserted-by":"crossref","first-page":"106442","DOI":"10.1016\/j.engappai.2023.106442","article-title":"Mixed local channel attention for object detection","volume":"123","author":"D Wan","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:31:09Z","timestamp":1762540269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335992"}},"subtitle":[],"editor":[{"given":"Fatih","family":"Uysal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":32,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0335992","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}