Research Article
Human Behavior Recognition Algorithm Based on HD-C3D Model
@INPROCEEDINGS{10.1007/978-3-031-55471-1_7, author={Zhihao Xie and Lei Yu and Qi Wang and Ziji Ma}, title={Human Behavior Recognition Algorithm Based on HD-C3D Model}, proceedings={Mobile Networks and Management. 13th EAI International Conference, MONAMI 2023, Yingtan, China, October 27-29, 2023, Proceedings}, proceedings_a={MONAMI}, year={2024}, month={3}, keywords={C3D model activation function background difference method image scaling improvement}, doi={10.1007/978-3-031-55471-1_7} }- Zhihao Xie
Lei Yu
Qi Wang
Ziji Ma
Year: 2024
Human Behavior Recognition Algorithm Based on HD-C3D Model
MONAMI
Springer
DOI: 10.1007/978-3-031-55471-1_7
Abstract
To address the problems of low recognition accuracy and long training time of the original C3D (Convolutional 3D) model, this paper proposes a modified method to improve its framework. Firstly, the Relu activation function in the hidden layer is replaced by the Hardswish function to allow more neurons to participate in parameter updating and to alleviate the problem of slow gradient convergence. Secondly, the dataset was optimised using the background difference method and the image scaling improvement respectively, and the optimised dataset was used for model training. The image scaling improvement combined with the activation function improvement results in a better HDs-C3D (Hardswish Data scaling - Convolutional 3D) model. Its accuracy on the training dataset reached 89.1%; meanwhile, the training time per round was reduced by about 25% when trained in the experimental environment of this paper.
