摘要
人体姿态估计是指从图像中检测人体各部分的位置并计算其方向和尺度信息,姿态估计的结果分二维和三维两种情况,而估计的方法分基于模型和无模型两种途径。本文首先介绍了人体姿态估计的研究背景和应用方向,然后对姿态估计的相关概念作了阐述,分析了姿态估计的输出表示,接着从人体目标检测和姿态估计两大类进行了详细分析和讨论,从实际应用的角度对各种方法做了理论上的比较和分析。最后,对相关研究还存在的问题和进一步研究的趋势作了归纳和总结。
Pose estimation from images is to detect the position where the human body is located in the image and computes the orientation and scale for each body part, the results of pose estimation is always classified as 2-D and 3-D, and the approaches to these results can be divided as model-based approaches and model-free approaches. In this paper we first give a simple and applications of pose estimation, then conceptions relevant to pose est introd lmatlons are different representations of the results produced are compared, the remaining part of on the human body detection and human pose estimation, which are discussed in deta to the background discussed, and the this paper focuses il, all the different methods are discussed theoretically by applicability, at the end of this paper. The problems remaining to be located are analyzed.
出处
《计算机工程与科学》
CSCD
北大核心
2011年第11期89-97,共9页
Computer Engineering & Science
基金
国家自然科学基金资助项目(60803071)
教育部博士点基金项目(200800061067)
关键词
人体姿态估计
目标检测
人体模型
单帧图像
human pose estimation
object detection
human body model
single image
