Recognition and simulation of parachute action based on continuous hidden Markov model
Xuan Gong, Liang Han, Jiangyun Wang, Maopeng Ran · 2017
Building a human-computer interactive parachute simulator is an efficient way to avoid the high risk and high cost of field parachute training. In this paper, a novel dynamic recognition and simulation approach of parachute training is developed. Firstly we process the skeletal data acquired by Kinect and enforce the indication of the trainees' parachute posture, where principle component analysis (PCA) is used to extract the key features. Then continuous hidden Markov model (CHMM) is modified, combined with Gauss mixed model (GMM), to recognize parachute action dynamically. Viterbi algorithm is improved to implement the recognition, and action animation is conducted to verify the efficiency. Empirical results suggest that our method is exactly a viable alternative during the recognition of parachute training.