基于动态分级的自适应运动目标处理SLAM算法  

Adaptive moving object processing SLAM algorithm based on scene dynamic classification

作　　者：王富强[1] 王强[1] 李敏[1] 杨盼 Wang Fuqiang;Wang Qiang;Li Min;Yang Pan(School of Transportation&Logistics Engineering,Wuhan University of Technology,Wuhan 430063,China)

机构地区：[1]武汉理工大学交通与物流工程学院,武汉430063

出　　处：《计算机应用研究》2023年第8期2361-2366,共6页Application Research of Computers

基　　金：国家重点研发计划资助项目(2022YFB4300300)。

摘　　要：针对移动机器人在动态环境中视觉同时定位和地图构建(visual simultaneous localization and mapping,VSLAM)精度低、鲁棒性差的问题,提出了一种自适应运动目标处理SLAM算法(adaptive dynamic SLAM,AD-SLAM)。基于对极几何约束的场景动态分级前端实时感知运行环境的动态变化。通过基于几何约束和运动概率的低动态环境动态特征和基于语义分割的高动态环境动态目标处理消除运动目标。在计算机视觉数据集TUM上进行实验验证,结果表明提出方案在复杂动态环境中保证算法实时性的前提下提升了移动机器人建图过程中定位的精度和鲁棒性。Aiming at the problem of low accuracy and poor robustness of visual simultaneous localization and mapping(VSLAM)in dynamic environment,this paper proposed an adaptive dynamic SLAM(AD-SLAM).The scene dynamic classification front-end based on epipolar geometry constraint perceived the dynamic changes of the working environment in real time.This method used the dynamic feature culling in low dynamic environment based on geometric constraints and moving probability and the dynamic target processing in high dynamic environment based on semantic segmentation to eliminate moving objects.Experimental verification on the computer vision dataset TUM shows that the proposed method can improve the accuracy and robustness of localization in the mapping process of mobile robots while ensuring the real-time performance of the algorithm.

关 键 词：同时定位和地图构建 动态环境 动态分级 对极几何 语义分割 运动概率 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]