文献类型：期刊文献

英文题名：Improved Spatio-Temporal Convolutional Neural Networks for Traffic Police Gestures Recognition

作者：Wu, Zhixuan[1]; Ma, Nan[1]; Cheung, Yiu-Ming[2]; Li, Jiahong[3]; He, Qin[4]; Yao, Yongqiang[1]; Zhang, Guoping[1]

第一作者：Wu, Zhixuan

通讯作者：Ma, Nan

机构：[1] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, College of Robotics, Beijing, 100101, China; [2] Hong Kong Baptist University, Department of Computer Science, Hong Kong, 999077, Hong Kong; [3] College of Robotics, Beijing Union University, Beijing, 100101, China; [4] Beijing Union University, Beijing, 100101, China

第一机构：北京联合大学北京市信息服务工程重点实验室|北京联合大学机器人学院

年份：2020

起止页码：109-115

外文期刊名：Proceedings - 2020 16th International Conference on Computational Intelligence and Security, CIS 2020

收录：EI(收录号：20211910316194)

基金：ACKNOWLEDGMENT We really thank anonymous reviewer’s constructive suggestions. This work was supported in part by a grant from the National Natural Science Foundation of China (No. 61871038, No. 61931012), Beijing Natural Science Foundation (No. 4182022), Premium Funding Project for Academic Human Resources Development in Beijing Union University (No. BPHR2020AZ02) and key Projects of National Social Science Fund (No. 19AGL025).

语种：英文

外文关键词：Computer vision - Large dataset - Convolution - Extraction - Convolutional neural networks - Aspect ratio - Long short-term memory - Gesture recognition - Human computer interaction - Feature extraction

摘要：In the era of artificial intelligence, human action recognition is a hot spot in the field of vision research, which makes the interaction between human and machine possible. Many intelligent applications benefit from human action recognition. Traditional traffic police gesture recognition methods often ignore the spatial and temporal information, so its timeliness in human computer interaction is limited. We propose a method that is Spatio-Temporal Convolutional Neural Networks (ST-CNN) which can detect and identify traffic police gestures. The method can identify traffic police gestures by using the correlation between spatial and temporal. Specifically, we use the convolutional neural network for feature extraction by taking into account both the spatial and temporal characteristics of the human actions. After the extraction of spatial and temporal features, the improved LSTM network can be used to effectively fuse, classify and recognize various features, so as to achieve the goal of human action recognition. We can make full use of the spatial and temporal information of the video and select effective features to reduce the computational load of the network. A large number of experiments on the Chinese traffic police gesture dataset show that our method is superior. ? 2020 IEEE.