Abstract:
Addressing the critical need for accurate fall event detection due to their potentially severe impacts, this paper introduces the Spatial Channel and Pooling Enhanced You Only Look Once version 5 small (SCPE-YOLOv5s) model. Fall events pose a challenge for detection due to their varying scales and subtle pose features. To address this problem, SCPE-YOLOv5s introduces spatial attention to the Efficient Channel Attention (ECA) network, which significantly enhances the model\'s ability to extract features from spatial pose distribution. Moreover, the model integrates average pooling layers into the Spatial Pyramid Pooling (SPP) network to support the multi-scale extraction of fall poses. Meanwhile, by incorporating the ECA network into SPP, the model effectively combines global and local features to further enhance the feature extraction. This paper validates the SCPE-YOLOv5s on a public dataset, demonstrating that it achieves a mean Average Precision of 88.29 %, outperforming the You Only Look Once version 5 small by 4.87 %. Additionally, the model achieves 57.4 frames per second. Therefore, SCPE-YOLOv5s provides a novel solution for fall event detection.
摘要:
解决由于潜在的严重影响而导致的准确跌倒事件检测的关键需求,本文介绍了空间信道和池化增强YouOnlyLookOnce版本5小(SCPE-YOLOv5s)模型。跌倒事件由于其变化的尺度和微妙的姿势特征而对检测提出了挑战。为了解决这个问题,SCPE-YOLOv5将空间注意力引入了高效信道注意力(ECA)网络,这显著增强了模型从空间姿态分布中提取特征的能力。此外,该模型将平均池化层集成到空间金字塔池(SPP)网络中,以支持跌倒姿势的多尺度提取。同时,通过将ECA网络纳入SPP,该模型有效地结合了全局和局部特征,进一步增强了特征提取。本文在公共数据集上验证了SCPE-YOLOv5,证明它达到了88.29%的平均精度,表现优于你只看一次版本5小4.87%。此外,该模型实现每秒57.4帧。因此,SCPE-YOLOv5s为跌倒事件检测提供了一种新颖的解决方案。