欢迎访问《兵工学报》官方网站,今天是

兵工学报 ›› 2025, Vol. 46 ›› Issue (6): 240443-.doi: 10.12382/bgxb.2024.0443

• • 上一篇    下一篇

YSG-SLAM:动态场景下基于YOLACT的实时语义RGB-D SLAM系统

翟伟光1, 王峰2,*, 马星宇1, 赵薇1, 孟鹏帅1   

  1. 1 太原理工大学 电子信息工程学院, 山西 太原 030002
    2 太原理工大学 电气与动力工程学院, 山西 太原 030002
  • 收稿日期:2024-06-05 上线日期:2025-06-28
  • 通讯作者:
    *邮箱:18334623829@163.com
  • 基金资助:
    山西省留学人员科技活动项目择优资助项目(20230063); 山西省重点研发计划项目(202102150101008)

YSG-SLAM:a Real-time Semantic RGB-D SLAM Based on YOLACT in Dynamic Scene

ZHAI Weiguang1, WANG Feng2,*, MA Xingyu1, ZHAO Wei1, MENG Pengshuai1   

  1. 1 College of Electronic and Information Engineering, Taiyuan University of Technology, Taiyuan 030002, Shanxi, China
    2 College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030002, Shanxi, China
  • Received:2024-06-05 Online:2025-06-28

摘要:

针对动态环境中实时定位与建图(Simultaneous Localization and Mapping,SLAM)算法位姿估计存在的定位漂移、实时性差等问题,提出一个名为YSG-SLAM的实时语义RGB-D SLAM系统。为了提高系统实时性,新增两个并行线程:一个用于获取二维语义信息的语义分割线程,一个语义建图线程。为优化系统在处理动态物体时的准确性和鲁棒性,YSG-SLAM引入快速动态特征剔除算法,并耦合漏检补偿模块来应对基于实时实例分割(You Only Look At Coefficients,YOLACT)算法可能出现的漏检情况,有效地提升了特征点剔除的精确度和系统的整体稳定性。为减少由特征点聚集引起的定位误差从而优化特征点的空间分布,设计自适应角点提取阈值计算方法,使特征分布更加均匀。语义建图线程充分利用二维语义信息与三维点云数据,可选择性构建语义地图和八叉树地图,提高了系统的环境感知能力及机器人在复杂环境下的相关任务执行能力。YSG-SLAM在德国慕尼黑工业大学数据集、Bonn数据集上进行了评估,相较于原ORB-SLAM2,各项定位误差下降达93%。实验结果表明,YSG-SLAM有效提升了系统实时性,定位精度高,且可构建两种地图,具有一定的实用价值。

关键词: 动态环境, 语义分割, 自适应阈值, 漏检补偿, 语义建图

Abstract:

Simultaneous localization and mapping (SLAM) algorithm has the issues such as localization drift and poor real-time performance in attitude estimation within dynamic environment.A real-time semantic RGB-D SLAM system named as YSG-SLAM is proposed.To enhance the system’s real-time performance,two parallel threads,one for semantic segmentation to obtain 2D semantic information and another for semantic mapping, are introduced.To improve the accuracy and robustness of the system in handling the dynamic objects,YSG-SLAM incorporates a fast dynamic feature removal algorithm and couples it with a missed detection compensation module to mitigate potential missed detections from YOLACT segmentation algorithm.This effectively enhances the feature point removal accuracy and overall system stability.To reduce the localization errors caused by feature point clustering and optimize the spatial distribution of feature points,an adaptive corner extraction threshold calculation method is designed to make the distribution of features more uniform.The semantic mapping thread makes full use of 2D semantic information and 3D point cloud data to optionally construct semantic maps and octree maps,thereby improving the environmental perception capability of system and the task execution ability of robots in complex environment.YSG-SLAM has been evaluated on TUM and Bonn datasets,showing a 93% reduction in various localization errors compared to the original ORB-SLAM2.Experimental results indicate that YSG-SLAM significantly improves real-time performance,has high localization accuracy,and can construct two types of maps.

Key words: dynamic environment, semantic segmentation, adaptive threshold, missed detection compensation, semantic mapping

中图分类号: