基于二维和三维人体姿态估计的跌倒检测OA
Fall detection based on 2D and 3D human pose estimation
针对现有跌倒检测技术普遍存在的误检漏检问题,提出联合二维和三维人体姿态估计的跌倒检测策略:基于 Mamba 模型设计 Mamba-Attention 注意力机制、改进 C3_M 模块,提出二维人体姿态估计算法 Mamba-Pose,提高二维人体关键点检测能力;融合 Flash-Attention、DCT 变换与低通滤波,提出三维人体姿态估计算法 FlashPose,提高二维人体关键点映射到三维空间的准确性和实时性;将 MambaPose、FlashPose 和 K 近邻分类器(KNN)结合,构建出一种高准确率实时跌倒检测方法MFKF.公共数据集上的实验结果表明:在COCO数据集上,MambaPose 算法与YOLOv7Pose 相比,AP 值提高了 2.5 个百分点,显著提升了二维人体关键点检测的准确性,而且小目标检测的置信度更高、处理低分辨率图像时鲁棒性更强;在 Human3.6M 数据集上,FlashPose 算法的 MPJPE 和 FPS 值分别达到 47.2 mm 和 314,优于 PoseFormerV2,准确性更高、计算速度更快;在 UR、Le2i 和 Multicam 这 3 个跌倒检测数据集上,本文 MFKF 方法的 F1、灵敏度、特异度、准确率均为最优,且 FPS 值均高于 22.7,实现了跌倒的准确和实时检测.代码及演示视频链接:https://github.com/xgli411/MFKF.
To address the problem of false positives and false negatives in the existing fall detection technologies,a fall detection strategy integrating two-dimensional and three-dimensional human pose estimation is proposed.Based on the Mamba model,the Mamba-Attention mechanism is designed,the C3_M module is enhanced,and the 2D human pose estimation algorithm MambaPose is introduced.By integrating Flash-Attention,DCT transform and low-pass filtering,the 3D human pose estimation algorithm FlashPose is proposed to improve the accuracy and real-time performance of mapping 2D human keypoints to 3D space.Finally,MFKF,a high accuracy real-time fall detection method,is constructed by combining MambaPose,FlashPose,and the KNN classifier.The experimental results on the public datasets show that:On the COCO dataset,the MambaPose algorithm improves the AP value by 2.5 percentage points compared with YOLOv7Pose,which significantly improves the accuracy of 2D human keypoint detection,and has higher confidence in small target detection and greater robustness when processing low-resolution images;on the Human3.6M dataset,the FlashPose al-gorithm's MPJPE and FPS values reach 47.2 mm and 314,respectively,which are better than Pose-FormerV2,with higher accuracy and faster computation speed;on the three fall detection datasets of UR,Le2i,and Multicam,the proposed MFKF method has the optimal F1,sensitivity,specificity,and accuracy indexes,and the FPS values are higher than 22.7,which realizes accurate and real-time detection of falls.Code and demonstration videos are available at https://github.com/xgli411/MFKF.
李现国;段显霖;杨彦利;蒋鹏;张磊
天津工业大学 电子与信息工程学院,天津 300387||沧州市天津工业大学研究院,河北 沧州 061000天津工业大学 电子与信息工程学院,天津 300387天津工业大学 电子与信息工程学院,天津 300387||沧州市天津工业大学研究院,河北 沧州 061000山东新巨龙能源有限责任公司,山东 巨野 274000山东新巨龙能源有限责任公司,山东 巨野 274000
信息技术与安全科学
跌倒检测二维人体姿态估计三维人体姿态估计K近邻分类器(KNN)Mamba模型
fall detection2D human pose estimation3D human pose estimationKNN classifierMamba model
《天津工业大学学报》 2026 (4)
80-88,95,10
天津市技术创新引导专项(23YDTPJC00290)
评论