A 3D Scene Perception Method Based on Uncertainty Modeling

被引:0
作者
Gao, Yi [1 ]
Wang, Zhongli [1 ]
Wang, Yingbo [1 ]
机构
[1] Beijing Jiaotong University, Beijing
来源
Jiqiren/Robot | 2024年 / 46卷 / 04期
关键词
dynamic Bayes network; mapping; object detection and tracking; scene perception; simultaneous localization; uncertainty model;
D O I
10.13973/j.cnki.robot.230171
中图分类号
学科分类号
摘要
This paper aims to address limitations in multi-task scene perception, including the lack of system modeling and analysis on the uncertainty in state estimation for tasks such as detection, tracking, mapping, and localization. The scene perception task is divided into foreground and background perception tasks, where the former involves the detection and tracking of foreground objects, and the latter focuses on robot localization and mapping tasks. To achieve multi-task perception in complex scenes, both tasks are integrated within a dynamic Bayesian network framework. The multi-task scene perception problem is modeled as a joint optimization and estimation problem of system state parameters. Bayesian posterior probability estimation is employed to model the state of each system parameter. Starting with the point cloud measurement noises from LiDAR sensors, the uncertainties in ground truth annotation and self-pose estimation in the object detection and tracking network are analyzed, and uncertainty models for point cloud measurements and labels are constructed, along with a tracking model based on prediction confidence. Additionally, the impact of localization errors on mapping uncertainty and target tracking tasks is analyzed. An iterative extended Kalman filter is used to optimize the estimation of the pose’s maximum posterior probability. The proposed method achieves scene perception in complex and large-scale dynamic environments. Experimental results on the KITTI and UrbanNav datasets demonstrate its effectiveness in addressing the impact of dynamic targets on environmental mapping in complex scenes, with high accuracy and robustness. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码:450 / 464
页数:14
相关论文
共 50 条
[21]   LBFormer: Scene Perception Segmentation Transformer Based on Local Block [J].
Zhang, Yongjie ;
He, Yunze ;
Deng, Baoyuan ;
Zhang, Xiaofei ;
Wang, Hongjin ;
Wang, Shi ;
Cheng, Liang ;
Wang, Yaonan .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2025, 21 (02) :1389-1398
[22]   Collaborative 3D Scene Reconstruction in Large Outdoor Environments Using a Fleet of Mobile Ground Robots [J].
Lewis, John ;
Lima, Pedro U. U. ;
Basiri, Meysam .
SENSORS, 2023, 23 (01)
[23]   Scene perception based visual navigation of mobile robot in indoor environment [J].
Ran, T. ;
Yuan, L. ;
Zhang, J. B. .
ISA TRANSACTIONS, 2021, 109 :389-400
[24]   Modeling spatial uncertainty of point features in feature-based RGB-D SLAM [J].
Belter, Dominik ;
Nowicki, Michal ;
Skrzypczynski, Piotr .
MACHINE VISION AND APPLICATIONS, 2018, 29 (05) :827-844
[25]   Modeling spatial uncertainty of point features in feature-based RGB-D SLAM [J].
Dominik Belter ;
Michał Nowicki ;
Piotr Skrzypczyński .
Machine Vision and Applications, 2018, 29 :827-844
[26]   Sigma-FP: Robot Mapping of 3D Floor Plans With an RGB-D Camera Under Uncertainty [J].
Matez-Bandera, Jose-Luis ;
Monroy, Javier ;
Gonzalez-Jimenez, Javier .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) :12539-12546
[27]   UAV Mapping and 3D Modeling as a Tool for Promotion and Management of the Urban Space [J].
Skondras, Alexandros ;
Karachaliou, Eleni ;
Tavantzis, Ioannis ;
Tokas, Nikolaos ;
Valari, Elena ;
Skalidi, Ifigeneia ;
Bouvet, Giovanni Augusto ;
Stylianidis, Efstratios .
DRONES, 2022, 6 (05)
[28]   UAV PHOTOGRAMMETRY FOR MAPPING AND 3D MODELING - CURRENT STATUS AND FUTURE PERSPECTIVES [J].
Remondino, F. ;
Barazzetti, L. ;
Nex, F. ;
Scaioni, M. ;
Sarazzi, D. .
INTERNATIONAL CONFERENCE ON UNMANNED AERIAL VEHICLE IN GEOMATICS (UAV-G), 2011, 38-1 (C22) :25-31
[29]   Digital modeling and 3D printing of reliefs and the possibilities of implementation in the training of artists [J].
Blanch-Gonzalez, Elena ;
Espinel, Jose C. .
ARTE INDIVIDUO Y SOCIEDAD, 2022, 34 (04) :1603-1620
[30]   Dynamic Semantic Occupancy Mapping Using 3D Scene Flow and Closed-Form Bayesian Inference [J].
Unnikrishnan, Aishwarya ;
Wilson, Joey ;
Gan, Lu ;
Capodieci, Andrew ;
Jayakumar, Paramsothy ;
Barton, Kira ;
Ghaffari, Maani ;
Wilson, Joseph .
IEEE ACCESS, 2022, 10 :97954-97970