LiDAR-Based 3-D Human Pose Estimation and Action Recognition for Medical Scenes

Aiming at the problem of insufficient patient care caused by limited medical resources, a medical human pose dataset is established, a 3-D human pose estimation and action recognition algorithm based on LiDARs is proposed. By adding shallow feature maps, combining prediction branches, and optimizing loss functions, the algorithm reduces the error caused by the occlusion and the small depth difference between human body and background, and improves the pose estimation performance. An action classifier adapted to patient poses is constructed using manually designed features. The recognition accuracy reaches 93.46% and the recognition speed reaches 42FPS on 3080Ti. Experimental results show that the algorithm performs better than other mainstream algorithms on the medical human pose dataset, and can effectively solve the problem of human pose recognition in medical scenes.