该项目使用YOLOv5深度学习框架来检测图像或视频中人体的五种基本行为:跌倒、站立、蹲下、坐下和跑步。YOLOv5(You Only Look Once v5)是一种高效的物体检测模型,能够快速准确地识别出图像中的目标。本项目具有以下特点: 图像检测:用户可以通过上传图片,系统将识别并标记出图像中人体的行为。视频检测:支持实时视频流或本地视频文件的行为检测,并实时显示检测结果。 技术栈
Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging:基于运动和区域感知的对抗性学习的热成像跌倒检测 Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging(一)摘
A Novel Approach for Fall Detection Using Thermal Imaging and a Stacking Ensemble of Autoencoder and 3D-CNN Models A Novel Approach for Fall Detection Using Thermal Imaging and a Stacking Ensemble