.png){kind=icon}
返回
A line based pose representation for human action recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.image.2013.01.005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we utilize a line based pose representation to recognize human actions in videos. We represent the pose in each frame by employing a collection of line-pairs, so that limb and joint movements are better described and the geometrical relationships among the lines forming the human figure are captured. We contribute to the literature by proposing a new method that matches line-pairs of two poses to compute the similarity between them. Moreover, to encapsulate the global motion information of a pose sequence, we introduce line-flow histograms, which are extracted by matching line segments in consecutive frames. Experimental results on Weizmann and KTH datasets emphasize the power of our pose representation, and show the effectiveness of using pose ordering and line-flow histograms together in grasping the nature of an action and distinguishing one from the others. (c) 2013 Elsevier B.V. All rights reserved.
Keyword:
Human motion
Action recognition
Pose similarity
Pose matching
Line-flow
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
S
IF:
2.7
论文数:
2.8K
被引数:
4.2K
机构
引用论文
Tracking disease progression by searching paths in a temporal network of biological processes.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Gate technology for 70 nm metal–oxide–semiconductor field-effect transistors with ultrathin (<2 nm) oxides70 nm金属-氧化物-半导体场效应晶体管（MOSFET）的超薄（<2 nm）栅极技术
PREAI
分享收藏Human action recognition using shape and CLG-motion flow from multi-view image sequencesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容