To address the issues of high computational cost, poor real-time performance, and difficulty in deployment on edge devices in existing fall detection algorithms, a lightweight fall detection model named WPD-YOLO based on YOLOv8n is proposed. First, Wise-IoU is introduced as a new regression loss function in YOLOv8n to reduce the negative impact of low-quality samples in the model and improve its convergence speed. Next, the LAMP pruning method is employed to compress the improved model, effectively reducing both the parameter count and computational load. Finally, the model is fine-tuned by channel knowledge distillation method, and the detection accuracy of the model is improved without additional parameters. Experimental results show that on the public Fall-Detection dataset, compared with YOLOv8n, the parameter count of WPD-YOLO is reduced by 74.42%, the computational complexity is reduced by 50%, the speed of processing is increased by 56 frames per second, while the mean average precision is increased by 0.4%, reaching 87.8%.
COLÓN-EMERICC S, MCDERMOTTC L, LEED S, et al. Risk assessment and prevention of falls in older community-dwelling adults: a review[J]. JAMA, 2024, 331(16): 1397-1406.
[2]
RASSEKHE, SNIDAROL. Survey on data fusion approaches for fall-detection[J]. Information Fusion, 2025, 114: 102696.
ALANAZIT, BABUTAINK, MUHAMMADG. A robust and automated vision-based human fall detection system using 3D multi-stream CNNs with an image fusion technique[J]. Applied Sciences, 2023, 13(12): 6916.
[7]
BANSALA, SHARMAR, KATHURIAM. A vision-based approach to enhance fall detection with fine-tuned faster R-CNN[C]//2023 International Conference on Advanced Computing & Communication Technologies (ICACCTech), 2023.
ZHAOB R, CUIQ, SONGR J, et al. Decoupled knowledge distillation[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 18-24, 2022, New Orleans, LA, USA. IEEE, 2022: 11943-11952
[11]
HUANGG M, SHENA, HUY X, et al. Optimizing yolov5s object detection through knowledge distillation algorithm[C]//2024 5th International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE),25-27 October 2024,Shenzhen, China.
[12]
SOHANM, SAIRAM T, RAMI REDDYC V. A review on YOLOv8 and its advancements[C]//International Conference on Data Intelligence and Cognitive Informatics. Singapore: Springer Nature Singapore, 2024: 529-545.
[13]
TONGZ J, CHENY H, XUZ W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[14]
LEEJ, PARKS, MOS, et al. Layer-adaptive sparsity for the magnitude-based pruning[C]//International Conference on Learning Representations.2021.
[15]
SHUC Y, LIUY F, GAOJ F, et al. Channel-wise knowledge distillation for dense prediction[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). October 10-17, 2021. Montreal, QC, Canada. IEEE, 2021: 5311-5320.
[16]
FANGG F, MAX Y, SONGM L, et al. DepGraph: towards any structural pruning[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 17-24, 2023, Vancouver, BC, Canada. IEEE, 2023: 16091-16101.