Realtimehumanmotionrecognitionviaspikingneuralnetwork资源-CSDN文库

55 浏览量 2021-02-07 13:52:07 上传评论收藏 463KB PDF 举报

资源推荐

资源详情

资源评论

Real time human motion recognition via spiking neural

network

Yang Jing

1

, Wu Qingyuan

2

, Huang Maiqi

3

and Luo Ting

4

Beijing Normal University, Zhuhai campus, Zhuhai, Guangdong, China

1

yangjing@bnuz.edu.cn;

2

wuqingyuan@bnuz.edu.cn;

3

huangmaiqi@outlook.com;

4

Gloria_LuoTing@163.com

Abstract. Real time human action recognition is to recognize the human motion type based on

skeleton movement in real time and is always a challenging task. In this paper, a novel method

is proposed to accomplish the classification by using Spiking neural network (SNN) which is

biology oriented neural network dealing with precise timing spikes. First, a new temporal

encoding scheme is used to encode the real time motion capture data into a series of spikes and

the according type of the motion is represented by a spike time. Second, a two-layered spiking

neural network is initiated and trained through a gradient descent learning algorithm. The

experimental results show that this method achieves a good learning precision and

generalization.

1. Introduction

With the rapid development of motion capture techniques and systems, more and more motion data are

available for human action recognition in the research area of computer vision. Especially depth

cameras can provide 3D depth data [1] of joint positions of the human skeleton which are showed in

figure 1. That may be more helpful in recognition of the motion type than just using 2D data. However

the depth map also increases the amount of the data and makes the recognition process more complex.

As we know the human body is an articulated system of rigid segments connected by joints. The shape

information carried by the contour can be extended to the 3D case for motion recognition [2]. The 3D

depth data not only facilitates a rather powerful human motion capturing technique, but also makes it

possible to efficiently model human-object interactions and intra-class variations [3].

Figure 1. Skeleton of human body.

本内容试读结束，登录后可阅读更多

下载后可阅读完整内容，剩余5页未读，立即下载

内容反馈

weixin_38596093

粉丝: 2
资源: 944

最新资源

资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！点击此处反馈

feedback-tip