Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3185-3190.DOI: 10.11772/j.issn.1001-9081.2023101465

• Multimedia computing and computer simulation • Previous Articles     Next Articles

ORB-SLAM2 algorithm based on dynamic feature point filtering and optimization of keyframe selection

Xukang KAN1, Gefei SHI1,2(), Xuerong YANG1   

  1. 1.School of Aeronautics and Astronautics,Sun Yat?sen University,Shenzhen Guangdong 518107,China
    2.Shenzhen Key Laboratory of Intelligent Microsatellite Constellation (Sun Yat?sen University),Shenzhen Guangdong 518107,China
  • Received:2023-10-27 Revised:2024-01-26 Accepted:2024-02-04 Online:2024-10-15 Published:2024-10-10
  • Contact: Gefei SHI
  • About author:KAN Xukang, born in 1998, M. S. candidate. His research interests include visual SLAM, semantic SLAM.
    YANG Xurong, born in 1981, Ph. D., associate professor. His research interests include distributed cooperative perception and control for aircraft, application of aircraft cooperative perception.
  • Supported by:
    Shenzhen Science and Technology Program(ZDSYS202106230918080)

基于动态特征点滤除与关键帧选择优化的ORB-SLAM2算法

阚绪康1, 史格非1,2(), 杨雪榕1   

  1. 1.中山大学 航空航天学院,广东 深圳 518017
    2.深圳市智能微小卫星星座技术与应用重点实验室(中山大学),广东 深圳 518017
  • 通讯作者: 史格非
  • 作者简介:阚绪康(1998—),男,安徽滁州人,硕士研究生,主要研究方向:视觉SLAM、语义SLAM
    史格非(1988—),男,黑龙江哈尔滨人,副教授,博士,主要研究方向:绳系航天器、航天动力学与控制、空间系留电梯动力学与控制 shigf@mail.sysu.edu.cn
    杨雪榕(1981—),男,新疆和田人,副教授,博士,主要研究方向:飞行器分布式协同感知与控制、飞行器协同感知应用。

Abstract:

The Simultaneous Localization And Mapping (SLAM) algorithm suffers from a decrease in localization accuracy when moving targets appear. Introducing instance segmentation and other algorithms can handle dynamic scenes, but it is difficult to ensure the real-time performance of SLAM algorithm. Additionally, camera shake during motion may lead to inaccurate keyframe selection and tracking loss. In response to the issues, an ORB-SLAM2 algorithm based on dynamic feature point filtering and optimization of keyframe selection was proposed to ensure the real-time performance of SLAM algorithm, and reduce the influence of dynamic feature points on the positioning accuracy of SLAM algorithm effectively. And simultaneously, the issue of inaccurate keyframe selection caused by camera shake was addressed. In the proposed algorithm, YOLOv5 algorithm was introduced on the basis of ORB-SLAM2 algorithm to identify moving targets. In the tracking thread, dynamic target feature points were filtered out, thereby achieving a balance between real-time performance and positioning accuracy of the algorithm. At the same time, a discriminative criterion based on inter-frame relative motion quantity was proposed for keyframe selection, thereby enhancing the accuracy of keyframe selection. Experimental results on freiburg3_walking_xyz dataset indicate that compared to ORB-SLAM2 algorithm, the proposed algorithm has a 38.54% reduction in average processing time and a 95.2% improvement in Root Mean Square Error (RMSE) accuracy of absolute trajectory error. It can be seen that the proposed algorithm can address the issues mentioned above effectively, enhance the positioning accuracy and precision of SLAM algorithm, and then improve the usability of the maps.

Key words: Visual Simultaneous Localization And Mapping (VSLAM), dynamic scene, ORB-SLAM2, keyframe selection, YOLOv5 (You Only Look Once version 5)

摘要:

同时定位与建图(SLAM)算法在有运动目标的情况下存在定位精度下降的问题,而引入实例分割等算法虽然可以应对动态场景,但难以保证SLAM算法的实时性,且在运动时相机抖动会导致关键帧选择不准确和跟踪易丢失的问题。针对上述问题,提出一种基于动态特征点滤除与关键帧选择优化的ORB-SLAM2算法,以保证SLAM算法的实时性,并有效减少动态特征点对SLAM算法定位精度的影响,同时应对由相机抖动造成的关键帧选择不准确的问题。所提算法通过在ORB-SLAM2算法的基础上引入YOLOv5算法识别运动目标,在跟踪线程滤除动态目标特征点,从而兼顾算法的实时性与定位精度。同时,在选择关键帧上提出一种基于帧间相对运动量的判别准则,从而提高关键帧选择的准确性。在freiburg3_walking_xyz数据集的上实验结果表明,与ORB-SLAM2算法相比,所提算法的平均耗时减少了38.54%,绝对轨迹误差中的均方根误差(RMSE)精度提高了95.2%。可见,所提算法能有效解决上述问题,提升SLAM算法的定位精度和准确性,进而提升地图的可用性。

关键词: 视觉同时定位与建图, 动态场景, ORB-SLAM2, 关键帧选择, YOLOv5

CLC Number: