This study aims to solve the problem of inaccurate motion recognition and modeling in the traditional human motion trajectory virtual experiment system due to the loss of motion posture during motion capture. A high-precision human motion trajectory virtual experiment system based on virtual reality technology is proposed. The system uses VR helmet, motion capture device Kinect V2 and Unity3D development platform to build a three-dimensional virtual environment, and collect and display human motion trajectory in real time. The extended Kalman filter algorithm is used to process the captured raw motion data to improve the accuracy of the motion trajectory; the genetic algorithm is used to dynamically optimize the human motion model, automatically adjust the parameters in the virtual environment, reduce system delay, and optimize the feedback time of user operations. The experimental results show that the proposed optimization scheme significantly improves the accuracy of the motion trajectory, user interaction experience and computing efficiency, and can provide a more accurate, smooth and efficient virtual experiment environment. The error does not exceed 0.3, and the input delay and feedback delay under different working conditions are less than 0.25 s. The innovation of this paper lies in the combination of Kalman filtering and genetic algorithm, which realizes the precise optimization and real-time feedback of human motion trajectory, effectively solves many limitations of traditional virtual experiment systems, and provides a new solution for the application of virtual reality technology in human motion analysis and virtual experiments.
Liu et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: