【作者】 罗大为； 郑颖； 张姗；

【Author】 LUO Da-wei;ZHENG Ying;ZHANG Shan;Beijing Key Laboratory of Information Service Engineering,Beijing Union University;

【机构】 北京联合大学北京市信息服务工程重点实验室；

【摘要】 人体姿态估计是计算机视觉领域中的一个重要研究方向,被广泛应用于人体活动分析、人机交互以及视频监视等方面。基于视觉的人体姿态评估主要是指从图像中检测出人体各部件位置以及其方向和尺度信息。本文主要将人体姿态评估方法从输入上分为基于深度图像和基于RGB图像两类方法,然后从个人检测与多人检测、传统方法与深度学习方法等多方面对基于视觉的人体姿态评估方法进行讨论,并对近些年所提方法的模型进行介绍,最后对当前研究的难点问题以及未来的发展趋势进行阐述。更多还原

【Abstract】 Human pose estimation is receiving increasing attention in the field of computer vision.It mainly detects the position,direction and scale information of each part of the human body from the image.It can be applied to human activity analysis,human-computer interaction and video surveillance.In this paper,human pose estimation method was divided into two kinds of methods,RGB-D image and RGB image.The method based on RGB image was discussed minutely,and the models in recent years were introduced in detail.In the end,some detailed discussions on research challenges and future directions in human action and pose recognition were also provided.更多还原