Research on human action recognition based on convolutional neural network

Peng Wang, Yuliang Yang*, Wanchong Li, Linhao Zhang, Mengyuan Wang, Xiaobo Zhang, Mengyu Zhu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

3 引用 (Scopus)

摘要

This paper proposes a human action recognition (HAR) algorithm based on convolutional neural network, which is used for human semaphore motion recognition. First, collecting datas in three scenarios and Deep Convolution Generative Adversarial Networks(DCGAN) is used to implement data enhancement to generate the dataset (DataSR). Then, the 1∗1 and 3∗3 convolution kernels are used to design the full convolution network and the model is further compressed using the group convolution to obtain the new model HARNET. Experiments show that the mAP of HARNET on the DataSR dataset is 94.36%, and the model size is 76M, which is 30% of the size of the YOLOv3 model.

源语言英语
主期刊名2019 28th Wireless and Optical Communications Conference, WOCC 2019 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781728106601
DOI
出版状态已出版 - 5月 2019
活动28th Wireless and Optical Communications Conference, WOCC 2019 - Beijing, 中国
期限: 9 5月 201910 5月 2019

出版系列

姓名2019 28th Wireless and Optical Communications Conference, WOCC 2019 - Proceedings

会议

会议28th Wireless and Optical Communications Conference, WOCC 2019
国家/地区中国
Beijing
时期9/05/1910/05/19

指纹

探究 'Research on human action recognition based on convolutional neural network' 的科研主题。它们共同构成独一无二的指纹。

引用此