A Descriptor Coping With Complicated Human Activities

摘要：

　　Human activity discrimination algorithms are concentrated ordinary to upright poses.The algorithms become unsuitable when persons are non-upright and in complicated poses.To solve this problem,this paper proposes a pose encoding descriptor - AMOP to describe human pose precisely.This descriptor is invariant to scale and direction,furthermore it has the feature of easy to compress,expandable and convenient to compute.Experiments verify the convenience and effectiveness of this descriptor.

关键词： Human activity non-upright activity descriptor discrimination AMOP

作者: Zuchun Ding Wenying Mo

作者单位: Department of Image Research Guangzhou Yangguang net Electronics Co. Ltd. Guangzhou, China

会议类型: 国际会议

会议名称: 2015 IEEE Advanced Information Technology, Electronic and Automation Control Conference(IAEAC 2015)(2015 IEEE先进信息技术,电子与自动化控制国际会议)

会议地点: 重庆

会议语种:英文

页码: 957-961

在线出版日期: 2015-12-19（万方平台首次上网日期，不代表论文的发表时间）