摘要
针对现有基于人体骨架的行为识别方法存在计算量大、不适合在线应用的问题,提出一种多骨架特征前期融合的在线行为识别算法。该算法通过前期嵌入层融合不同类型的输入特征,并结合最大池化和层次池化操作提取骨架空间的多语义信息。根据日常行为的数据特征设计有效的骨架序列选取方式,并制作NTU-GAST Skeleton数据集,实现在线的行为识别应用。在公开数据集NTU60/120 RGB+D上进行测试,结果表明提出的算法需要更少计算量的同时取得了较高的识别准确率。
Existing skeleton-based action recognition methods require large computation,which makes them unsuitable for online applications.Aiming at this problem,this paper proposes an online skeleton-based action recognition method with multi-feature early fusion.The algorithm integrated different types of input feature through the early embedding layer and combined the max pooling and hierarchical pooling to extract multi-semantic spatial information.The selection strategy of skeleton sequences was designed based on the characteristics of daily actions.A new 3D skeleton dataset,NTU-GAST Skeleton,was made for online action recognition.Experiments on NTU60 and 120 RGB+D dataset indicate that the proposed method achieves higher recognition accuracy with less computational complexity.
作者
刘均发
黎奕辉
Liu Junfa;Li Yihui(School of Electromechanical Engineering,Guangdong University of Technology,Guangzhou 510006,Guangdong,China)
出处
《计算机应用与软件》
北大核心
2024年第1期161-167,共7页
Computer Applications and Software
基金
广东省前沿与关键技术创新专项项目(2017B050506008)
广东省重点领域研发计划项目(2019B090915001)。
关键词
多骨架特征
前期融合
行为识别
在线应用
Multi-skeleton feature
Early fusion
Action recognition
Online application
