基于YOLOv8改进的室内行人跌倒检测算法FDW-YOLO  

FDW-YOLO:An improved indoor pedestrian fall detection algorithm based on YOLOv8

作　　者：陈晨[1] 徐慧英[1] 朱信忠[1] 黄晓[2] 宋杰 曹雨淇 周思瑜 盛轲 CHEN Chen;XU Hui-ying;ZHU Xin-zhong;HUANG Xiao;SONG Jie;CAO Yu-qi;ZHOU Si-yu;SHENG Ke(School of Computer Science and Technology(School of Articial Intelligence),Zhejiang Normal University,Jinhua 321004;College of Education,Zhejiang Normal University,Jinhua 321004,China)

机构地区：[1]浙江师范大学计算机科学与技术学院(人工智能学院),浙江金华321004 [2]浙江师范大学教育学院,浙江金华321004

出　　处：《计算机工程与科学》2024年第8期1455-1465,共11页Computer Engineering & Science

基　　金：国家自然科学基金(62376252,61976196);浙江省自然科学基金重点项目(LZ22F030003);国家级大学生创新创业训练计划项目创新训练重点项目(202310345042)。

摘　　要：针对室内场景中由于光照变化、人体形态被遮挡以及在特殊视角下人体姿态变化等因素导致行人跌倒检测精度低、实时性差的问题,提出了一种基于YOLOv8改进的轻量级跌倒检测算法FDW-YOLO。将骨干网络中的C2f模块替换成FasterNext模块,增强有效特征复用的同时降低计算复杂度。根据人体跌倒姿势变化大的特点,设计了3种在颈部层不同位置添加动态可变形卷积模块的网络结构,并在自制的跌倒行为目标检测数据集上进行实验比较,最终根据网络性能选择YOLOv8-C方案。在改进后的网络中引入边界框回归损失函数WIoU取代原有的CIoU。实验结果表明,FDW-YOLO跌倒检测算法较YOLOv8n在mAP@0.5指标上从96.5%提升到97.9%,在mAP@0.5:0.95指标上从72.5%提升到74.3%,同时参数量和计算量只有4.1×10^(6)和7.3×10^(9),符合在低算力工业场景中部署的要求。Aiming at the problem of low fall detection accuracy and poor real-time performance in indoor scenes due to the effects of light change,occlusion of the human body form,and changes in the human body posture under special viewpoint,a lightweight improved fall detection algorithm based on YOLOv8,named FDW-YOLO,is proposed.The C2f module in the backbone network is replaced by the FasterNext module,which reduces the computational complexity while retaining the excellent feature extraction capability.According to the characteristics of human falls with large changes in posture,three network structures with dynamically deformable convolutional modules added at different positions in the neck layer are designed,experiments are conducted on a self-made fall dataset for comparison,and ultimately,the YOLOv8-C scheme is selected based on network performance.A bounding box regression loss function WIoU is introduced into the improved network to replace the original CIoU.The experimental results show that compared with YOLOv8n,the FDW-YOLO fall detection algorithm increases mAP@0.5 from 96.5%to 97.9%and mAP@0.5:0.95 from 72.5%to 74.3%,while the number of parameters and computation is only 4.1×10^(6)and 7.3×10^(9),which is in line with the requirements for deployment in low-computing power industrial scenarios.

关 键 词：目标检测 跌倒 FasterNext DDConv WIoU 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]