Abstract
To prevent convulsions and falls of patients in the absence of medical staff, it is crucial to monitor their physical condition in hospital wards. However, several unresolved challenges in human joint recognition remain, such as object occlusion, human self-occlusion and complex backgrounds, resulting in difficulties in its practical application. In this paper, a multi-LiDAR system is proposed to obtain a multi-view human body point cloud. An improved V2V-Posenet model was introduced to detect the actual position of the human joint. In this system, each point cloud was spliced into a full point cloud and voxelized into the model. We also used a random voxel zero setting for data enhancement, constraining the relative length between human joints into a loss function and three-dimensional Gaussian filtering in a heat map for model learning. The improved model exhibited excellent performance in detecting human joints in hospital wards. The experimental results showed that the improved model achieved 91.6 % mean average precision, compared to 80.1 % for the original model and 77.4 % for the comparison algorithm A2J-Posenet. The speed of the improved model meets the requirements for real-time target detection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have