人体关节运动检测与跟踪综述
李旭1,杨达伟1,罗霞1,孙淼2
(1.东方汽轮机有限公司,四川 德阳 618000;2.四川省机械研究设计院,四川 成都 610063)
摘要:讨论了计算机视觉检测和追踪算法在人体关节运动跟踪中的应用,以及此类算法在其他方面的应用,回顾了近几十年来关于人体关节运动检测和跟踪算法的研究现状,综述了检测和跟踪算法的大致分类。检测类算法主要包括PAF、Associative Embedding、Part Segmentation和Mid-Range offsets,跟踪类算法主要包括卡尔曼滤波、粒子滤波、mean shift、KCF。简述了各算法的主要思路及其优缺点,给出了用于评价各个算法的指标。最后,还展望了跟踪算法的发展趋势和未来的研究重点,强调了具有实际应用价值的长期跟踪算法,同时提出了改进追踪效果的三个重要方向。
关键词:计算机视觉;人体关节运动;检测算法;跟踪算法
中图分类号:R322.7+2 文献标志码:A doi:10.3969/j.issn.1006-0316.2020.08.004
文章编号:1006-0316 (2020) 08-0018-06
Review on the Human Body Joint Motion Detecting and Tracking
LI Xu1,YANG Dawei1,LUO Xia1,SUN Miao2
( 1.DONG FANG TURBINE CO., LTD., De Yang 618000, China; 2. Sichuan Provincial Machinery Research and Design Institute, Chengdu 610063, China )
Abstract:In this paper, the application of computer vision based detecting and tracking algorithms in human body joint motion and other fields is discussed, and a rough classification of the detecting and tracking algorithms based on the history of the development of the detecting and tracking algorithms about human body joint motion is introduced. detecting algorithms mainly includes PAF, Associative Embedding, Part Segmentation and Mid-Range offsets, and tracking algorithms mainly includes Kalman Filtering,Particle Filtering,mean Shift and KCF. The advantages and disadvantages of these algorithms are explained briefly, and the evaluation standard for each algorithm is presented. Finally, the development trend and the key points of the future research are predicted, and the practical value of long-term tracking algorithms is emphasized. Meanwhile, three crucial ways to improve the tracking performance are proposed.
Key words:computer vision;human joint motion;detecting algorithm;tracking algorithm
———————————————
收稿日期:2020-02-24
作者简介:李旭(1977-),男,四川资阳人,本科,高级工程师,主要研究方向为机械设计及制造。*通讯作者:孙淼(1987-),男,四川德阳人,工学硕士,工程师,主要研究方向为机构学、机电控制。
 

 

设为首页  |  加入收藏    |   免责条款
《机械》杂志版权所有     Copyright©2008-2012 Jixiezazhi.com All Rights Reserved 

  电话:028-85925070    传真:028-85925073    E-mail:jixie@vip.163.com

地址:四川省成都锦江工业开发区墨香路48号   邮编:610063

蜀ICP备08103512号

Powered by PageAdmin CMS