SLAM Method Based on Visual Features in Dynamic Scene

doi:10.19678/j.issn.1000-3428.0056013

Abstract

Abstract: As a research hotspot in the field of robotics,Simultaneous Localization and Mapping(SLAM) has made great progress in recent years,but few SLAM methods take dynamic or movable targets in the application scene into account.To handle the problem,this paper proposes a SLAM method which introduces the deep learning-based object detection algorithm into the classic ORB_SLAM2 method to make it more suitable for dynamic scene.The feature points are divided into dynamic feature points and potential dynamic feature points.The motion model is calculated based on dynamic feature points,which is used to select the static feature points in the application scene for pose tracking,and select static feature points in the dynamic feature points for map construction.Experimental results on KITTI and TUM datasets show that compared with the ORB_SLAM2 system,the proposed method improves the tracking accuracy and the application performance of the map.

Key words: Simultaneous Localization and Mapping(SLAM), local feature, dynamic scene, deep learning, object detection

摘要： 同时定位与地图构建（SLAM）作为机器人领域的研究热点，近年来取得了快速发展，但多数SLAM方法未考虑应用场景中的动态或可移动目标。针对该问题，提出一种适用于动态场景的SLAM方法。将基于深度学习的目标检测算法引入到经典ORB_SLAM2方法中，将特征点分为潜在动态特征点和非潜在动态特征点，基于非潜在动态特征点计算运动模型，筛选出应用场景中的静态特征点并实现位姿跟踪，利用非潜在动态特征点中的静态特征点进行地图构建。KITTI和TUM数据集上的实验结果表明，与ORB_SLAM2系统相比，该方法能够提高跟踪轨迹精度与地图的适用性。

关键词: 同时定位与地图构建, 局部特征, 动态场景, 深度学习, 目标检测

CLC Number:

TP391

ZHANG Jinfeng, SHI Chaoxia, WANG Yanqing. SLAM Method Based on Visual Features in Dynamic Scene[J]. Computer Engineering, 2020, 46(10): 95-102.

张金凤, 石朝侠, 王燕清. 动态场景下基于视觉特征的SLAM方法[J]. 计算机工程, 2020, 46(10): 95-102.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0056013

http://www.ecice06.com/EN/Y2020/V46/I10/95

Figures/Tables 11

References

[1] MUR-ARTAL R,MONTIEL J M M,TARDOS J D.ORB-SLAM:a versatile and accurate monocular SLAM system[J].IEEE Transactions on Robotics,2015,31(5):1147-1163.
[2] MUR-ARTAL R,TARDOS J D.ORB-SLAM2:an open-source SLAM system for monocular,stereo,and RGB-D cameras[J].IEEE Transactions on Robotics,2017,33(5):1255-1262.
[3] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of 2011 International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:152-168.
[4] FANG Y Q,DAI B.An improved moving target detecting and tracking based on optical flow technique and Kalman filter[C]//Proceedings of 2009 International Conference on Computer Science & Education.Washington D.C.,USA:IEEE Press,2009:1197-1202.
[5] WANG Y B,HUANG S D.Towards dense moving object segmentation based robust dense RGB-D SLAM in dynamic scenarios[C]//Proceedings of 2014 International Conference on Control Automation Robotics & Vision (ICARCV).Washington D.C.,USA:IEEE Press,2014:1841-1846.
[6] BESCOS B,FACIL J M,CIVERA J,et al.DynaSLAM:tracking,mapping,and inpainting in dynamic scenes[J].IEEE Robotics and Automation Letters,2018,3(4):4076-4083.
[7] HE K M,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):386-397.
[8] YU C,LIU Z X,LIU X J,et al.DS-SLAM:a semantic visual SLAM towards dynamic environments[C]//Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems.Washington D.C.,USA:IEEE Press,2018:1168-1174.
[9] KONSTANTINOS N L.VSO:Visual Semantic Odometry[EB/OL].[2019-08-23].https://openaccess.thecvf.com/content_ECCV_2018/papers/Konstantinos-Nektarios_Lianos_VSO_Visual_Semantic_ECCV_2018_paper.pdf.
[10] SZEGEDY C,REED S,ERHAN D,et al.Scalable,high-quality object detection[EB/OL].[2019-08-23].https://arxiv.org/abs/1412.1441.
[11] WEN X Z,SHAO L,FANG W,et al.Efficient feature selection and classification for vehicle detection[J].IEEE Transactions on Circuits and Systems for Video Technology,2015,25(3):508-517.
[12] KOTUS J,LOPATKA K,CZYZEWSKI A.Detection and localization of selected acoustic events in acoustic field for smart surveillance applications[J].Multimedia Tools and Applications,2014,68(1):5-21.
[13] WU T F,LI B,ZHU S C.Learning and-or model to represent context and occlusion for car detection and viewpoint estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(9):1829-1843.
[14] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:886-893.
[15] ZHANG Zhenwei,SHI Chaoxia.Fast image retrieval method using improved bag of visual words model[J].Computer Systems Applications,2016,25(12):126-131.(in Chinese)张祯伟,石朝侠.改进视觉词袋模型的快速图像检索方法[J].计算机系统应用,2016,25(12):126-131.
[16] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[17] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[18] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:580-587.
[19] GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1440-1448.
[20] REDMON J,FARHADI A.YOLOv3:an incremental improvement[EB/OL].[2019-08-23].https://arxiv.org/abs/1804.02767.
[21] HE Li,ZHOU Chuanwei,ZHANG Kun,et al.Binary feature matching approach based on sequential sampling evaluation[J].Computer Engineering,2017,43(8):316-321.(in Chinese)贺黎,周传伟,张坤,等.基于顺序采样评估的二进制特征匹配方法[J].计算机工程,2017,43(8):316-321.

Please choose a citation manager

Content to export