.png){kind=icon}
返回
Human action recognition based on multi-scale feature maps from depth video sequences
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-021-11193-4.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Human action recognition is an active research area in computer vision. Although great progress has been made, previous methods mostly recognize actions from depth video sequences at only one scale, and thus they often neglect multi-scale spatial changes that provide additional information in practical applications. In this paper, we present a novel framework with a multi-scale mechanism to improve scale diversity of motion features. We propose a multi-scale feature map called Laplacian pyramid depth motion images(LP-DMI). First, We employ depth motion images (DMI) as the templates to generate the multi-scale static representation of actions. Then, we caculate LP-DMI to enhance multi-scale dynamic information of motions and reduce redundant static information in human bodies. We further extract the multi-granularity descriptor called LP-DMI-HOG to provide more discriminative features. Finally, we utilize extreme learning machine (ELM) for action classification. The proposed method yeilds the recognition accuracy of 93.41%, 85.12%, 91.94% on the public MSRAction3D, UTD-MHAD and DHA dataset. Through extensive experiments, we prove that our method outperforms the state-of-the-art benchmarks.
Keyword:
Action recognition
Laplacian pyramid
Multi-scale motion representation
Extreme learning machine
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Incentive mechanisms for smartphone collaboration in data acquisition and distributed computing
PREAI
分享收藏
Depth Sequential Information Entropy Maps and Multi-Label Subspace Learning for Human Action Recognition用于人体动作识别的深度序列信息熵图和多标记子空间学习.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容