TOTAL VIEWS: 3271
The action of a character is composed of a 3D matrix of 20 three-dimensional coordinate points. The 20 points are the coordinates of the bones of the character's body. I divided the 1,000 data into four types of character actions. Now I use the Naive Bayes model and the linear Gaussian model to analyze the human skeleton coordinates, and judge which model is more suitable for human skeletal action prediction through the accuracy of the test set and the results of the confusion matrix. Of course, We can also use the character Actions are divided into more categories. We can capture specific actions to determine the behavioral state of the characters, and identify actions that endanger others. In the security field, this behavioral state of characters can help identify dangerous rioters so that we can take precautions in advance.
[1] D. Berry. Statistics—A Bayesian Perspective. Duxbury Press, 1996.
[2] P. Domingos, M. Pazzani. On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning, 29 (2) (1997) 103-130.
[3] N. A. Zaidi, J. Cerquides, M. J. Carman, G. I. Webb. Alleviating naive Bayes attribute independence assumption by attribute weighting. Journal of Machine Learning Research, 14 (2013) 1947-198.
[4] S. Villa, M. Rossetti. Learning continuous time Bayesian network classifiers using MapReduce. Journal of Statistical Software, 62 (3) (2014), 1-2.
[5] C. Andrieu, N. de Freitas, A. Doucet, and M.I. Jordan. An introduction to MCMC for machine learning. Machine Learning, 50(1-2):5-43, 2003.
[6] Z. Ghahramani and G. Hinton. The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1, Department of Computer Science, University of Toronto, 1996. Available.
Human Skeleton Coordinate Pose Recognition
How to cite this paper: Aodi Ding. (2022). Human Skeleton Coordinate Pose Recognition. Engineering Advances, 2(2), 194-197.
DOI: http://dx.doi.org/10.26855/ea.2022.12.010