基于实例分割的动态场景视觉SLAM  

Visual SLAM in dynamic scenarios based on instance segmentation

作　　者：李庚 吴丽君[1] LI Geng;WU Lijun(College of Physics and Information Engineering,Fuzhou University,Fuzhou 350108,Fujian,China)

机构地区：[1]福州大学物理与信息工程学院,福建福州350108

出　　处：《微电子学与计算机》2023年第10期29-37,共9页Microelectronics & Computer

基　　金：国家自然科学基金项目(62271151);福建省自然科学基金项目(2022H0008,2021J01)。

摘　　要：视觉同时定位与建图技术已成为移动机器人和无人驾驶等领域的一个研究热点.目前,大多数视觉SLAM假设周围环境为静态的,当场景中存在运动物体时容易失效.为此,本文基于视觉图像的语义和几何信息来剔除环境中的运动物体,以提升系统的鲁棒性.具体地,本工作在ORB-SLAM2的基础上,通过多线程机制实现轻量级网络获取语义信息,以剔除已知类型的动态对象,并设计一个和语义剔除紧耦合的几何检测模块来剔除未知类型的运动物体.为平衡实时性与建图鲁棒性,在平台处理能力不足时,采用只对关键帧剔除动态点的策略.在TUMRGB-D的动态环境数据集的实验结果表明,本文算法在动态环境下的定位精度相较ORB-SLAM2有显著提升;与其他动态SLAM相比,精度也有一定程度的提升.Visual simultaneous localization and mapping technology has become a research hotspot in the fields of mobile robots and unmanned driving.At present,most visual SLAM assumes that the surrounding environment is static,and it is easy to fail when there are moving objects in the scene.To this end,this paper eliminates moving objects in the environment based on the semantic and geometric information of visual images to improve the robustness of the system.Specifically,on the basis of ORB-SLAM2,this work implements a lightweight network to obtain semantic information through a multi-threading mechanism to eliminate known types of dynamic objects,and designs a geometric detection module tightly coupled with semantic elimination to eliminate unknown type of moving objects.In order to balance the real-time performance and the robustness of map construction,when the processing capacity of the platform is insufficient,the strategy of only removing dynamic points for key frames is adopted.The experimental results on the dynamic environment dataset of TUM RGB-D show that the positioning accuracy of the algorithm in the dynamic environment is significantly improved compared with ORB-SLAM2;compared with other dynamic SLAM,the accuracy is also improved to a certain extent.

关 键 词：同时定位与建图 动态场景 实例分割 几何检测 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]