数字适老视角下基于MAR-YOLO的路面防跌倒检测方法与产品设计

徐秋莹; 陈炬; 晏合敏

doi:10.19554/j.cnki.1001-3563.2026.12.023

PDF(13253 KB)

包装工程（设计栏目） ›› 2026, Vol. 47 ›› Issue (12) : 287-297. DOI: 10.19554/j.cnki.1001-3563.2026.12.023

设计研讨

数字适老视角下基于MAR-YOLO的路面防跌倒检测方法与产品设计

徐秋莹¹, 陈炬^1,*, 晏合敏²

作者信息 +

Road Surface Fall-prevention Detection Method and Product Design Based on MAR-YOLO from a Digital Age-friendly Perspective

XU Qiuying¹, CHEN Ju^1,*, YAN Hemin²

Author information +

文章历史 +

摘要

目的旨在解决老年人因路面湿滑导致的跌倒风险问题,通过提出一种轻量化实时检测模型以及相关产品设计,提升老年人出行安全并降低跌倒事故发生率。方法基于改进的MAR-YOLO算法（MobileNetV4-AFPN-ResCBAM-YOLOv11）。首先采用MobileNetV4作为主干网络实现模型轻量化设计;其次引入渐近特征金字塔网络（AFPN）增强多尺度特征融合能力;最后融合ResCBAM注意力机制以提升关键特征提取效率,从而显著增强模型在复杂环境下的检测鲁棒性。结果所提出模型在湿滑路面检测任务中表现优异,精确率达到98.5%,召回率为90.1%,在保持高精确率的同时实现了模型的轻量化与快速检测,满足实际部署需求。结论研究进一步设计了面向老年人的防跌倒系统及配套产品方案。方案将轻量化深度学习技术与主动预防机制有机结合,不仅为智慧城市助老设施建设提供了技术支撑,也为辅助技术领域的创新应用提供了实践参考。

Abstract

The work aims to propose a lightweight real-time detection model along with related product designs to address the issue of fall risks among the elderly caused by slippery road surfaces, and enhance outdoor safety and reduce the incidence of falls. Based on the improved MAR-YOLO algorithm (MobileNetV4-AFPN-ResCBAM-YOLOv11), MobileNetV4 was used as the backbone network for lightweight model design. The asymptotic feature pyramid network (AFPN) was incorporated to enhance the multi-scale feature fusion capability, and the ResCBAM attention mechanism was integrated to improve the efficiency of key feature extraction, thereby significantly boosting detection robustness in complex environments. Experimental results demonstrated that the proposed model achieved outstanding performance in slippery road surface detection, with a precision of 98.5% and a recall rate of 90.1%, fulfilling practical deployment requirements by maintaining high accuracy while ensuring lightweight and rapid detection. The study further designs a fall prevention system and corresponding product solutions for the elderly, effectively integrating lightweight deep learning technology with proactive prevention mechanisms. This work not only provides technical support for the development of smart city elderly-care facilities, but also offers practical references for innovative applications in assistive technology.

导出引用1

徐秋莹, 陈炬, 晏合敏. 数字适老视角下基于MAR-YOLO的路面防跌倒检测方法与产品设计[J]. 包装工程. 2026, 47(12): 287-297 https://doi.org/10.19554/j.cnki.1001-3563.2026.12.023

XU Qiuying, CHEN Ju, YAN Hemin. Road Surface Fall-prevention Detection Method and Product Design Based on MAR-YOLO from a Digital Age-friendly Perspective[J]. Packaging Engineering. 2026, 47(12): 287-297 https://doi.org/10.19554/j.cnki.1001-3563.2026.12.023

中图分类号： TB472

参考文献

[1] World Health Organization. Population ageing[EB/OL]. (2025-02-21)[2025-11-10]. https://www.who.int/news-room/questions-and-answers/item/population-ageing.
[2] United Nations. World Population Ageing 2020 Highlightsc https://www.un.org/development/desa/pd/sites/www.un.org.development.desa.pd/files/undesa_pd-2020_world_population_ageing_highlights.pdf.
[3] ZHU H L, HU K, LIU S Y, et al.Systematic Causality Mapping of Factors Leading to Accidental Falls of Older Adults[J]. Public Health in Practice, 2020, 1: 100045.
[4] MIKOS M, TRYBULSKA A, CZERW A.Falls - the Socio-Economic and Medical Aspects Important for Developing Prevention and Treatment Strategies[J]. Annals of Agricultural and Environmental Medicine, 2021, 28(3): 391-396.
[5] MEHTA J, BAIG A.The Importance of Assessing Vision in Falls Management: A Narrative Review[J]. Optometry and Vision Science, 2025, 102(2): 10.
[6] GAYA-MOREY F X, MANRESA-YEE C, BUADES- RUBIO J M. Deep Learning for Computer Vision Based Activity Recognition and Fall Detection of the Elderly: A Systematic Review[EB/OL]. (2024-05-10)[2026-06- 25]. 11790. https://arxiv.org/abs/2401.11790.
[7] DORMOSH N, SCHUT M C, HEYMANS M W, et al.Development and Internal Validation of a Risk Prediction Model for Falls among Older People Using Primary Care Electronic Health Records[J]. The Journals of Gerontology: Series A, 2022, 77(7): 1438-1445.
[8] CHEN X D, HE L X, SHI K W, et al.Interpretable Machine Learning for Fall Prediction among Older Adults in China[J]. American Journal of Preventive Medicine, 2023, 65(4): 579-586.
[9] LU L, ZHANG J Y, XIE Y, et al.Wearable Health Devices in Health Care: Narrative Systematic Review[J]. JMIR MHealth and UHealth, 2020, 8(11): e18907.
[10] HADER G K, BEN ISMAIL M M, BCHIR O. Automatic Fall Detection Using Region-Based Convolutional Neural Network[J]. International Journal of Injury Control and Safety Promotion, 2020, 27(4): 546-557.
[11] MARZIYEH GHORESHI BEYRAMI S, GHADERYAN P. A Robust, Cost-Effective and Non-Invasive Computer-Aided Method for Diagnosis Three Types of Neurodegenerative Diseases with Gait Signal Analysis[J]. Measurement, 2020, 156: 107579.
[12] TUNCA C, SALUR G, ERSOY C.Deep Learning for Fall Risk Assessment with Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait Parameters[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(7): 1994-2005.
[13] LEE Y, POKHAREL S, AL MUSLIM A, et al.Experimental Study: Deep Learning-Based Fall Monitoring among Older Adults with Skin-Wearable Electronics[J]. Sensors, 2023, 23(8): 3983.
[14] CLEMENTE J, LI F Y, VALERO M, et al.Smart Seismic Sensing for Indoor Fall Detection, Location, and Notification[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(2): 524-532.
[15] KALINGA T, SIRITHUNGE C, BUDDHIKA A G, et al.A Fall Detection and Emergency Notification System for Elderly[C]// 2020 6th International Conference on Control, Automation and Robotics (ICCAR). Singapore: IEEE, 2020: 706-712.
[16] WANG X Y, ELLUL J, AZZOPARDI G.Elderly Fall Detection Systems: A Literature Survey[J]. Frontiers in Robotics and AI, 2020, 7: 71.
[17] MEYER C, RENEHAN E, BATCHELOR F, et al.'Falls Not a Priority': Insights on Discharging Older People, Admitted to Hospital for a Fall, back to the Community[J]. Australian Journal of Primary Health, 2018, 24(1): 66-73.
[18] DEL DIN S, KIRK C, YARNALL A J, et al.Body-Worn Sensors for Remote Monitoring of Parkinson's Disease Motor Symptoms: Vision, State of the Art, and Challenges Ahead[J]. Journal of Parkinson's Disease, 2021, 11(s1): S35-S47.
[19] LIU-AMBROSE T, DAVIS J C, BEST J R, et al.Effect of a Home-Based Exercise Program on Subsequent Falls among Community-Dwelling High-Risk Older Adults after a Fall: A Randomized Clinical Trial[J]. Jama, 2019, 321(21): 2092.
[20] SMITH M L, TOWNE S D, HERRERA-VENSON A, et al.Delivery of Fall Prevention Interventions for At-Risk Older Adults in Rural Areas: Findings from a National Dissemination[J]. International Journal of Environmental Research and Public Health, 2018, 15(12): 2798.
[21] SUN R P, SOSNOFF J J.Novel Sensing Technology in Fall Risk Assessment in Older Adults: A Systematic Review[J]. BMC Geriatrics, 2018, 18(1): 14.
[22] SABOOR A, KASK T, KUUSIK A, et al.Latest Research Trends in Gait Analysis Using Wearable Sensors and Machine Learning: A Systematic Review[J]. IEEE Access, 2020, 8: 167830-167864.
[23] 陈殿生, 申振阳, 尹虎. 防跌倒步态平衡训练机器人发展现状[J]. 包装工程, 2022, 43(12): 75-86.
CHEN D S, SHEN Z Y, YIN H.Development Status of Anti-Fall Gait Balance Training Robot[J]. Packaging Engineering, 2022, 43(12): 75-86.
[24] PARAMASIVAM A, FERLIN DEVA SHAHILA D, JENATH M, et al. Development of Artificial Intelligence Edge Computing Based Wearable Device for Fall Detection and Prevention of Elderly People[J]. Heliyon, 2024, 10(8): e28688.
[25] HANIF M, AHMAD T, ASLAM M, et al.Towards an Accessible Agent for Blind's Self Localization and Navigational Assistance[J]. International Journal of Computers and Applications, 2025, 47(6): 487-496.
[26] HUANG L H, CHANG H D, CUI K J, et al.A Detection System for Road Surface Slippery Condition Based on Convolutional Neural Networks[J]. Automot. Appl. Technol. 2022;47(6):18-21.
[27] SHIM S, CHUN C J, RYU S K.Road Surface Damage Detection Based on Object Recognition Using Fast R-CNN[J]. The Journal of the Korea Institute of Intelligent Transport Systems, 2019, 18(2): 104-113.
[28] PHAM V, PHAM C, DANG T.Road Damage Detection and Classification with Detectron2 and Faster R-CNN[C]//2020 IEEE International Conference on Big Data (Big Data). Atlanta: IEEE, 2021: 5592-5601.
[29] YANG X F, LI X T, YE Y M, et al.Road Detection and Centerline Extraction via Deep Recurrent Convolutional Neural Network U-Net[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9): 7209-7220.
[30] REDMON J, DIVVALA S, GIRSHICK R, et al.You Only Look Once: Unified, Real-Time Object Detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 779-788.
[31] WANG D D, HE D J.Channel Pruned YOLO V5s-Based Deep Learning Approach for Rapid and Accurate Apple Fruitlet Detection Before Fruit Thinning[J]. Biosystems Engineering, 2021, 210: 271-281.
[32] LIU X Y, WANG T, YANG J M, et al.MPQ-YOLO: Ultra Low Mixed-Precision Quantization of YOLO for Edge Devices Deployment[J]. Neurocomputing, 2024, 574: 127210.
[33] KHOLIAVCHENKO M. Iterative Low-Rank Approximation for CNN Compression [J]. arXiv preprint arXiv:1803.08995, 2018.
[34] XING Z Q, CHEN X, PANG F Q.DD-YOLO: An Object Detection Method Combining Knowledge Distillation and Differentiable Architecture Search[J]. IET Computer Vision, 2022, 16(5): 418-430.
[35] QIN D F, LEICHNER C, DELAKIS M, et al.MobileNetV4: Universal Models for the mobile Ecosystem[C]// Computer Vision - ECCV 2024. Cham: Springer, 2025: 78-96.
[36] TAN M, LE Q.Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks[C]// International Conference on Machine Learning. Long Beach: PMLR, 2019: 6105-6114.
[37] HAN K, WANG Y H, TIAN Q, et al.GhostNet: More Features from Cheap Operations[C]// 2020IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020: 1577-1586.
[38] DU F J, JIAO S J.Improvement of Lightweight Convolutional Neural Network Model Based on YOLO Algorithm and Its Research in Pavement Defect Detection[J]. Sensors, 2022, 22(9): 3537.
[39] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 936-944.
[40] YANG G Y, LEI J, ZHU Z K, et al.AFPN: Asymptotic Feature Pyramid Network for Object Detection[C]// 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Honolulu: IEEE, 2024: 2184-2189.
[41] 杨明旭, 张俊宁, 张志强, 等. 基于改进YOLOv8的药片泡罩包装缺陷检测算法[J]. 包装工程, 2025, 46(1): 145-154.
YANG M X, ZHANG J N, ZHANG Z Q, et al.Defect Detection Algorithm of Pharmaceutical Blister Package Based on Improved YOLOv8[J]. Packaging Engineering, 2025, 46(1): 145-154.
[42] JOCHER G, QIU J, CHAURASIA A. Ultralytics YOLO11[EB/OL]. (2024-09-27)[2025-11-10]. https://github.com/ultralytics/ultralytics.