本文基于深度学习的语义提取技术和视觉SLAM(simultaneous local-ization and mapping)技术相结合,提出了一种动态SLAM算法.该算法基于三类对象的投票和语义回环,能够有效地降低动态对象对SLAM系统的性能影响,同时提高定位和建图的精度.首先,将语义对象分为静态对象、可能动态对象和一定动态对象三类,并使用基于重投影深度误差投票的方法来识别上述语义对象的运动状态,从而消除运动目标对算法的影响.然后,进一步地使用语义相似回环优化方法,提高了回环检测的鲁棒性.在TUM的RGB-D动态数据集和KITTI数据集上的实验结果表明,本文算法的平均绝对轨迹误差相比ORB-SLAM3算法分别降低了57.13％和23.39％,验证了算法在动态场景下的鲁棒性.
Dynamic SLAM Algorithm Based on Voting of Three Objects and Semantic Loop Closure
We introduce a dynamic simultaneous localization and mapping(SLAM)algorithm,combi-ning deep learning-based semantic segmentation with visual SLAM.As a conclusion,this algo-rithm utilizes voting based on three categories of objects and semantic loop closures to effectively mitigate the impact of dynamic objects on SLAM system performance,while enhancing localization and mapping accuracy.Firstly,the semantic objects are classified into three categories:static,potentially dynamic,and certainly dynamic.Then voting method is employed based on reprojection depth error to identify the motion states of these semantic objects,thereby negating the influence of moving targets.Additionally,we employ a semantic similarity loop closure optimization method to enhance loop closure detection robustness.Experimental results on the TUM RGB-D dynamic data-set and the KITTI dataset demonstrate that our algorithm reduces the average absolute trajectory er-ror by 57.13％and 23.39％compared to the ORB-SLAM3 algorithm,respectively,confirming its robustness in dynamic scenes.
dynamic SLAM(simultaneous localization and mapping)semantic segmentationloop closure detection
国家科技期刊平台
NSTL
万方数据
