《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (8): 2537-2545.DOI: 10.11772/j.issn.1001-9081.2022070972

• 多媒体计算与计算机仿真 • 上一篇    下一篇

动态环境下视觉定位与建图的运动分割研究进展

朱东莹1, 钟勇2, 杨观赐1,3,4(), 李杨3   

  1. 1.贵州大学 机械工程学院,贵阳 550025
    2.中国科学院 成都计算机应用研究所,成都 610213
    3.现代制造技术教育部重点实验室(贵州大学),贵阳 550025
    4.省部共建公共大数据国家重点实验室(贵州大学),贵阳 550025
  • 收稿日期:2022-07-06 修回日期:2022-09-19 接受日期:2022-09-19 发布日期:2023-01-15 出版日期:2023-08-10
  • 通讯作者: 杨观赐
  • 作者简介:朱东莹(1996—),男,浙江杭州人,硕士研究生,CCF会员,主要研究方向:自主智能系统
    钟勇(1966—),男,四川岳池人,研究员,博士,主要研究方向:大数据及其智能处理、云计算、软件工程
    李杨(1993—),男,河南安阳人,博士研究生,主要研究方向:自主智能系统。
  • 基金资助:
    国家自然科学基金资助项目(62163007);贵州省科技计划项目(黔科合平台人才[2020]6007,黔科合支撑[2021]一般439)

Research progress on motion segmentation of visual localization and mapping in dynamic environment

Dongying ZHU1, Yong ZHONG2, Guanci YANG1,3,4(), Yang LI3   

  1. 1.School of Mechanical Engineering,Guizhou University,Guiyang Guizhou 550025,China
    2.Chengdu Institute of Computer Application,Chinese Academy of Sciences,Chengdu Sichuan 610213,China
    3.Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education (Guizhou University),Guiyang Guizhou 550025,China
    4.State Key Laboratory of Public Big Data (Guizhou University),Guiyang Guizhou 550025,China
  • Received:2022-07-06 Revised:2022-09-19 Accepted:2022-09-19 Online:2023-01-15 Published:2023-08-10
  • Contact: Guanci YANG
  • About author:ZHU Dongying, born in 1996, M. S. candidate. His research interests include intelligent autonomous system.
    ZHONG Yong, born in 1966, Ph. D., research fellow. His research interests include big data and intelligent processing, cloud computing, software engineering.
    LI Yang, born in 1993, Ph. D. candidate. His research interests include intelligent autonomous system.
  • Supported by:
    National Natural Science Foundation of China(62163007);Science and Technology Program of Guizhou Province(Qiankehepingtairencai[2020]6007)

摘要:

动态环境中视觉定位与建图系统受环境中动态物体的影响,定位与建图误差增加同时鲁棒性下降。而对输入图像的运动分割可显著提高动态环境下视觉定位与建图系统的性能。动态环境中的动态物体可分为运动物体与潜在运动物体。当前动态物体识别方法存在运动主体混乱、实时性差的问题。因此,综述了视觉定位与建图系统在动态环境下的运动分割策略。首先,从场景的预设条件出发,将运动分割策略分为基于图像主体静止假设方法、基于先验语义知识的方法和不引入假设的多传感融合方法;然后,对这三类方法进行总结,并分析各方法的准确性和实时性;最后,针对视觉定位与建图系统在动态环境下运动分割策略的准确性、实时性难以平衡的问题,讨论并展望了动态环境下运动分割方法的发展趋势。

关键词: 视觉定位与建图, 动态环境, 运动分割, 实时性, 移动机器人

Abstract:

Visual localization and mapping system is affected by dynamic objects in a dynamic environment, so that it has increase of localization and mapping errors and decrease of robustness. And motion segmentation of input images can significantly improve the performance of visual localization and mapping system in dynamic environment. Dynamic objects in dynamic environment can be divided into moving objects and potential moving objects. Current dynamic object recognition methods have problems of chaotic moving subjects and poor real-time performance. Therefore, motion segmentation strategies of visual localization and mapping system in dynamic environment were reviewed. Firstly, the strategies were divided into three types of methods according to preset conditions of the scene: methods based on static assumption of image subject, methods based on prior semantic knowledge and multi-sensor fusion methods without assumption. Then, these three types of methods were summarized, and their accuracy and real-time performance were analyzed. Finally, aiming at the difficulty of balancing accuracy and real-time performance of motion segmentation strategy of visual localization and mapping system in dynamic environment, development trends of the motion segmentation methods in dynamic environment were discussed and prospected.

Key words: visual localization and mapping, dynamic environment, motion segmentation, real-time performance, mobile robot

中图分类号: