Escalator Passenger Safety Detection YOLO_BFROI Algorithm Based on Region of Interest

doi:10.3778/j.issn.1002-8331.2404-0405

Abstract

Abstract: Intelligent monitoring of escalators is an important means of preventing passenger accidents. However, the operating environment of escalators is complex with small target passenger detection, which can easily lead to missed and false detection. Therefore, a region of interest-based escalator passenger fall detection algorithm using the improved YOLOv8 is proposed in this paper. Firstly, the BiFormer_ROI attention mechanism module based on regions of interest is designed, and a small object detection module group of SPD-Conv and BiFormer_ROI is constructed to improve the YOLOv8 backbone network, so as to shield the complex environmental interference of non-escalator background areas and effectively improve the small targets detection rate. Secondly, considering the practical industrial applications, GhostSlimPAFPN lightweight structure is adopted to optimize the Neck network, which effectively reduces the number of model parameters while maintaining detection accuracy. Finally, the PIoU v2 loss function with target size adaptive penalty factor is adopted to improve the Head network, thereby achieving faster convergence and higher detection precision. On the self-built escalator passenger fall dataset, the experimental results show that the improved algorithm achieves 94.2% average detection precision and 87.7?FPS detection speed. It can effectively reduce false and missed detection, which can better ensure the safety of passengers on the elevator.

Key words: deep learning, escalator, fall detection, YOLOv8 algorithm, regions of interest, lightweight

摘要： 自动扶梯智能化监控是预防乘客事故发生的重要手段，然而扶梯运行环境较复杂，背景干扰严重，远距离小目标乘客的检测容易造成漏检和误检问题，提出一种基于感兴趣区域改进YOLOv8的轻量化自动扶梯乘客摔倒检测算法。改进算法设计了基于感兴趣区域的BiFormer_ROI注意力机制模块，构造SPD-Conv和BiFormer_ROI的小目标检测模块组改进YOLOv8骨干网络，屏蔽非扶梯背景区域的复杂环境干扰，有效提高小目标检测率。考虑实际应用需要采用GhostSlimPAFPN轻量化结构优化Neck网络，在保持检测精度的同时有效减少模型参数量。采用具有目标尺寸自适应惩罚因子的PIoU v2损失函数改进Head网络，从而实现更快的收敛和更高的检测精度。在自建扶梯乘客摔倒数据集上，改进算法乘客摔倒平均检测精度达到94.2%，检测帧率为87.7?FPS，检测性能显著提高，能有效减少漏检和误检问题，且具有良好的实时性，可以更好地保障乘客安全乘梯。

关键词: 深度学习, 自动扶梯, 摔倒检测, YOLOv8算法, 感兴趣区域, 轻量化

HOU Ying, HU Xin, ZHAO Ruirui, ZHANG Nan, XU Yanhong, MA Li. Escalator Passenger Safety Detection YOLO_BFROI Algorithm Based on Region of Interest[J]. Computer Engineering and Applications, 2025, 61(6): 84-95.

侯颖, 胡鑫, 赵瑞瑞, 张楠, 徐艳红, 马莉. 感兴趣区域YOLO_BFROI的扶梯乘客安全检测算法[J]. 计算机工程与应用, 2025, 61(6): 84-95.

References

[1] XING Y Y, CHEN S D, ZHU S X, et al. Analysis factors that influence escalator-related injuries in metro stations based on Bayesian networks: a case study in China[J]. International Journal of Environmental Research and Public Health, 2020, 17(2): 481.
[2] OSIPOV V, ZHUKOVA N, SUBBOTIN A, et al. Intelligent escalator passenger safety management[J]. Scientific Reports, 2022, 12: 5506.
[3] GUTIéRREZ J, RODRíGUEZ V, MARTIN S. Comprehensive review of vision-based fall detection systems[J]. Sensors, 2021, 21(3): 947.
[4] ALAM E, SUFIAN A, DUTTA P, et al. Vision-based human fall detection systems using deep learning: a review[J]. Computers in Biology and Medicine, 2022, 146: 105626.
[5] 周燕, 刘紫琴, 曾凡智, 等. 深度学习的二维人体姿态估计综述[J]. 计算机科学与探索, 2021, 15(4): 641-657.
ZHOU Y, LIU Z Q, ZENG F Z, et al. Survey on two-dimensional human pose estimation of deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(4): 641-657.
[6] WU L, HUANG C, FEI L K, et al. Video-based fall detection using human pose and constrained generative adversarial network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(4): 2179-2194.
[7] YIN Y W, LEI L, LIANG M H, et al. Research on fall detection algorithm for the elderly living alone based on YOLO[C]//Proceedings of the IEEE Conference on Emergency Science and Information Technology (ICESIT 2021), 2021: 403-408.
[8] RAZA A, YOUSAF M H, VELASTIN S A. Human fall detection using YOLO: a real-time and AI-on-the-edge perspective[C]//Proceedings of the 12th International Conference on Pattern Recognition Systems (ICPRS), 2022: 1-6.
[9] ZHAO D A, SONG T, GAO J, et al. YOLO-fall: a novel convolutional neural network model for fall detection in open spaces[J]. IEEE Access, 2024, 12: 26137-26149.
[10] 杨学存, 李杰华, 陈丽媛, 等. 基于人体骨架的扶梯乘客异常行为识别方法[J]. 安全与环境学报, 2024, 24(2): 636-643.
YANG X C, LI J H, CHEN L Y, et al. An abnormal behavior recognition method of escalator passengers based on human skeletons[J]. Journal of Safety and Environment, 2024, 24(2): 636-643.
[11] 滕安. 基于人体姿态识别的行人乘坐自动扶梯跌倒检测方法的研究[D]. 大连: 大连交通大学, 2019.
TENG A. Research of falling detection method of pedestrians taking the escalator based on human pose recognition[D]. Dalian: Dalian Jiaotong University, 2019.
[12] 汪威, 胡旭晓, 吴跃成, 等. 基于深度学习的自动扶梯视频人体动作识别[J]. 软件工程, 2021, 24(9): 24-27.
WANG W, HU X X, WU Y C, et al. Human motion recognition in escalator video based on deep learning[J]. Software Engineering, 2021, 24(9): 24-27.
[13] 林创鲁, 叶亮, 李刚, 等. 基于深度学习的自动扶梯乘客异常行为识别方法研究[J]. 自动化与信息工程, 2022, 43(6): 1-6.
LIN C L, YE L, LI G, et al. Research on identification method of escalator passengers’ abnormal behavior based on deep learning[J]. Automation & Information Engineering, 2022, 43(6): 1-6.
[14] NOOR N, PARK I K. A lightweight skeleton-based 3D-CNN for real-time fall detection and action recognition[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023: 2179-2188.
[15] 王源鹏, 万海斌, 黄凯, 等. 基于YOLOv5s的自动扶梯乘客异常行为实时检测算法[J]. 激光与光电子学进展, 2024, 61(8): 211-218.
WANG Y P, WAN H B, HUANG K, et al. Real-time detection of abnormal behavior of escalator passengers based on YOLOv5s[J]. Laser & Optoelectronics Progress, 2024, 61(8): 211-218.
[16] 梁博. 基于视频的自动扶梯行人摔倒实时检测算法[D]. 太原: 山西大学, 2024.
LIANG B. Real-time detection algorithm of escalator figure falling based on video[D]. Taiyuan: Shanxi University, 2024.
[17] 许腾. 基于计算机视觉的自动扶梯跌倒检测算法研究[D]. 福州: 福建工程学院, 2023.
XU T. A study of computer vision-based escalator fall detection algorithm[D]. Fuzhou: Fujian University of Technology, 2023.
[18] 侯颖, 杨林, 胡鑫, 等. 基于SwinT-YOLOX模型的自动扶梯行人安全检测算法[J]. 计算机工程, 2024, 50(3): 277-289.
HOU Y, YANG L, HU X, et al. Automatic escalator pedestrian safety detection algorithm based on SwinT-YOLOX model[J]. Computer Engineering, 2024, 50(3): 277-289.
[19] 邵延华, 张铎, 楚红雨, 等. 基于深度学习的YOLO目标检测综述[J]. 电子与信息学报, 2022, 44(10): 3697-3708.
SHAO Y H, ZHANG D, CHU H Y, et al. A review of YOLO object detection based on deep learning[J]. Journal of Electronics & Information Technology, 2022, 44(10): 3697-3708.
[20] 杨锋, 丁之桐, 邢蒙蒙, 等. 深度学习的目标检测算法改进综述[J]. 计算机工程与应用, 2023, 59(11): 1-15.
YANG F, DING Z T, XING M M, et al. Review of object detection algorithm improvement in deep learning[J]. Computer Engineering and Applications, 2023, 59(11): 1-15.
[21] JOCHER G, CHAURASIA A, STOKEN A, et al. Ultralytics/YOLOv5: v6.1[EB/OL]. (2022-02-22). https://github.com/ultralytics/YOLOv5/releases/tag/v6.1.
[22] LI C Y, LI L L, JIANG H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[23] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state- of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.
[24] JOCHER G, CHAURASIA A, QIU J, et al. Ultralytics/YOLOv8: v8.1.0[EB/OL]. (2024-01-10). https://github.com/ultralytics/ultralytics/tree/v8.1.0.
[25] 张艳, 张明路, 吕晓玲, 等. 深度学习小目标检测算法研究综述[J]. 计算机工程与应用, 2022, 58(15): 1-17.
ZHANG Y, ZHANG M L, LYU X L, et al. Review of research on small target detection based on deep learning[J]. Computer Engineering and Applications, 2022, 58(15): 1-17.
[26] ZHU L, WANG X J, KE Z H, et al. BiFormer: vision transformer with bi-level routing attention[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 10323-10333.
[27] SUNKARA R, LUO T. No more strided convolutions or pooling: a new CNN building block for low-resolution images and?small objects[C]//Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2022: 443-459.
[28] SUN R Y, FAN H, TANG Y J, et al. Research on small target detection algorithm for UAV inspection scene based on SPD-conv[C]//Proceedings of the Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023), 2024: 686-691.
[29] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
[30] HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
[31] LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv:2206.02424, 2022.
[32] LIU C, WANG K G, LI Q, et al. Powerful-IoU: more straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism[J]. Neural Networks, 2024, 170: 276-284.
[33] LI X, WANG W H, WU L J, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[C]//Advances in Neural Information Processing Systems, 2020: 21002-21012.