基于光线碰撞检测的轻量化实时三维重建系统

陈昌川; 丁锡烽; 王亦何; 孙霞; 乔飞

doi:10.12263/DZXB.20230983

您当前的位置：

首页 >

文章列表页 >

基于光线碰撞检测的轻量化实时三维重建系统

学术论文 | 更新时间：2025-12-11

- 基于光线碰撞检测的轻量化实时三维重建系统
- Lightweight Real-Time 3D Reconstruction System Based on Light Collision Detection
- 电子学报 2024年52卷第12期页码：4074-4086
- 作者机构：
  
  1.重庆邮电大学通信与信息工程学院，重庆 400065
  2.清华大学电子工程系，北京 100084
  3.重庆工程学院电子信息学院，重庆 400056
- 作者简介：
  
  [ "陈昌川男，1978年10月出生，四川广安人.重庆邮电大学通信学院副教授.主要研究方向为智能信息处理、图像处理与人工智能、特高频局放检测、红外成像与测温.E-mail: creditdegree@gmail.com" ]
  [ "丁锡烽男，1999年8月出生，重庆万州人.重庆邮电大学通信学院硕士研究生.主要研究方向为视觉SLAM和三维重建. E-mail: S210131034@stu.cqupt.edu.cn" ]
  [ "王亦何男，2006年5月出生，甘肃白银人.清华大学电子系本科生.主要研究方向为SLAM算法、三维建图算法. E-mail: wangyihe21@mails.tsinghua.edu.cn" ]
  [ "孙霞女，1976年9月出生，河南周口人.重庆工程学院电子学院副教授.主要研究方向为多智能体系统、智能算法、数字信号处理. E-mail: 51552654@qq.com" ]
  [ "乔飞男，1977年11月出生，山西太原人.清华大学电子系副研究员.主要研究方向为低功耗集成电路设计、“感算共融”智能感知集成电路和系统. E-mail: qiaofei@tsinghua.edu.cn" ]
- 基金信息：
  
  新疆维吾尔自治区重点研发计划(2022B01008-3);国家自然科学基金(92164203;62334006);重庆市教委重点项目(KJZD-K202301901);重庆市科委项目(2023NSCQ-MSX4308);陕西省重点研发计划(2023-YBNY-222)
- DOI：10.12263/DZXB.20230983
  中图分类号： TP242;TP391
- 收稿：2023-10-19，
  
  修回：2024-07-08，
  
  纸质出版：2024-12-25
- 稿件说明：
移动端阅览
陈昌川, 丁锡烽, 王亦何, 等. 基于光线碰撞检测的轻量化实时三维重建系统[J]. 电子学报, 2024, 52(12): 4074-4086.

CHEN Chang-chuan, DING Xi-feng, WANG Yi-he, et al. Lightweight Real-Time 3D Reconstruction System Based on Light Collision Detection[J]. Acta Electronica Sinica, 2024, 52(12): 4074-4086.
陈昌川, 丁锡烽, 王亦何, 等. 基于光线碰撞检测的轻量化实时三维重建系统[J]. 电子学报, 2024, 52(12): 4074-4086. DOI：10.12263/DZXB.20230983

CHEN Chang-chuan, DING Xi-feng, WANG Yi-he, et al. Lightweight Real-Time 3D Reconstruction System Based on Light Collision Detection[J]. Acta Electronica Sinica, 2024, 52(12): 4074-4086. DOI：10.12263/DZXB.20230983

摘要

针对小型机器人在复杂环境中进行实时定位与建图时，存在机载端CPU（Central Processing Unit）计算资源不足，建图精度差、探索效率低的问题.本文提出一种基于同时定位与建图（Simultaneous Localization and Mapping，SLAM）、截断符号距离函数（Truncated Signed Distance Function，TSDF）实时的三维重建方法.该方法基于深度相机或双目相机获取重建目标及场景的RGB（Red Green Blue）图和深度图，同时基于ORB_SLAM2获取位姿信息；采用基于特征点云数据的表面重建算法TSDF与深度图相结合，实现一种实时三维场景重建；为了降低三维重建模型与真实场景的误差，提出一种采用光线碰撞检测融合特征点的方法，并结合优化策略减小光线投影距离与体素到物体表面距离的误差.通过优化后的TSDF值，保证了重建场景的完整性.在ASL（Autonomous Systems Lab）开源数据集上，相比于Voxblox、Voxfield和VDBblox，该系统三维重建模型的均方根误差分别下降了55.6%、47.11%、21.7%，相比于Voxblox、Voxfield，系统地图更新速率分别提升了9.7%和12.9%.最后，将该系统用于室内场景实验，地图平均每帧更新速率为7.35 ms/帧，验证了所提系统的可行性和有效性.

Abstract

When small robots perform real-time positioning and mapping in complex environments

there are problems such as insufficient computing resources of the onboard CPU (Central Processing Unit)

poor mapping accuracy

and low exploration efficiency. This paper proposes a real-time 3D reconstruction method based on simultaneous localization and mapping (SLAM) and truncated signed distance function (TSDF). This method obtains the RGB (Red Green Blue) image and depth image of the reconstructed target and scene based on a depth camera or a binocular camera

and obtains the pose information based on ORB_SLAM2. The surface reconstruction algorithm TSDF based on feature point cloud data is combined with the depth map to achieve a real-time 3D scene reconstruction. In order to reduce the error between the 3D reconstructed model and the real scene

a method of fusing feature points using light collision detection is proposed

and the error between the light projection distance and the distance from the voxel to the object surface is reduced by combining the optimization strategy. The integrity of the reconstructed scene is guaranteed by the optimized TSDF value. In ASL (Autonomous Systems Lab) the system is used in an open source dataset of the 3D reconstruction model of the proposed system. Compared with Voxblox

Voxfield and VDBblox

the root mean square error of the system's 3D reconstruction model is reduced by 55.6%

47.11% and 21.7% respectively. Compared with Voxblox and Voxfield

the system map update rate is increased by 9.7% and 12.9% respectively. Finally

the system is used in indoor scene experiments

and the average map update rate is 7.35 ms/frame

which verifies the feasibility and effectiveness of the proposed system.

关键词

Keywords

references

JIA P S . Research on positioning and navigation of medical robot based on RGB-D visual SLAM [C ] // 2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) . Piscataway : IEEE , 2023 : 627 - 632 .

代少升 , 刘小兵 , 赖智颖 , 等 . 网格化局部自适应DBSCAN聚类算法 [J ] . 重庆邮电大学学报(自然科学版) , 2022 , 34 ( 2 ): 250 - 257 .

DAI S S , LIU X B , LAI Z Y , et al . Gridded local adaptive DBSCAN clustering algorithm [J ] . Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition) , 2022 , 34 ( 2 ): 250 - 257 . (in Chinese)

郭艺轩 , 贾向东 , 曹胜男 , 等 . 三维动态无人机网络覆盖性能与信道容量分析 [J ] . 重庆邮电大学学报(自然科学版) , 2022 , 34 ( 4 ): 662 - 668 .

GUO Y X , JIA X D , CAO S N , et al . Analysis of 3D dynamic UAV network coverage performance and channel capacity [J ] . Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition) , 2022 , 34 ( 4 ): 662 - 668 . (in Chinese)

陈孟元 , 韩朋朋 , 刘金辉 , 等 . 动态遮挡场景下基于改进Transformer实例分割的VSLAM算法 [J ] . 电子学报 , 2023 , 51 ( 7 ): 1812 - 1825 .

CHEN M Y , HAN P P , LIU J H , et al . Improved transformer instance segmentation under dynamic occlusion based VSLAM algorithm [J ] . Acta Electronica Sinica , 2023 , 51 ( 7 ): 1812 - 1825 . (in Chinese)

陈昌川 , 全锐杨 , 张谦 , 等 . 基于轻量化智能的多机协同SLAM系统 [J ] . 仪器仪表学报 , 2022 , 43 ( 12 ): 188 - 198 . CHEN C C , QUAN R Y , ZHANG Q , et al . Lightweight intelligence-based multi-machine collaborative SLAM system [J ] . Chinese Journal of Scientific Instrument , 2022 , 43 ( 12 ): 188 - 198 . (in Chinese)

NEWCOMBE R A , IZADI S , HILLIGES O , et al . KinectFusion: Real-time dense surface mapping and tracking [C ] // 2011 10th IEEE International Symposium on Mixed and Augmented Reality . Piscataway : IEEE , 2011 : 127 - 136 .

LIU K , SUN H X , YE P . Research on bundle adjustment for visual SLAM under large-scale scene [C ] // 2017 4th International Conference on Systems and Informatics (ICSAI) . Piscataway : IEEE , 2017 : 220 - 224 .

WHELAN T , JOHANNSSON H , KAESS M , et al . Robust real-time visual odometry for dense RGB-D mapping [C ] // 2013 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2013 : 5724 - 5731 .

ZENG M , ZHAO F K , ZHENG J X , et al . Octree-based fusion for realtime 3D reconstruction [J ] . Graphical Models , 2013 , 75 ( 3 ): 126 - 136 .

ENDRES F , HESS J , STURM J , et al . 3-D mapping with an RGB-D camera [J ] . IEEE Transactions on Robotics , 2014 , 30 ( 1 ): 177 - 187 .

ZHANG T W , ZHANG H Y , LI Y , et al . FlowFusion: Dynamic dense RGB-D SLAM based on optical flow [C ] // 2020 IEEE International Conference on Robotics and Automation (ICRA) . Piscataway : IEEE , 2020 : 7322 - 7328 .

OLEYNIKOVA H , TAYLOR Z , FEHR M , et al . Voxblox: Incremental 3D euclidean signed distance fields for on-board MAV planning [C ] // 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Piscataway : IEEE , 2017 : 1366 - 1373 .

PAN Y , KOMPIS Y , BARTOLOMEI L , et al . Voxfield: Non-projective signed distance fields for online planning and 3D reconstruction [C ] // 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Piscataway : IEEE , 2022 : 5331 - 5338 .

REIJGWART V , MILLANE A , OLEYNIKOVA H , et al . Voxgraph: Globally consistent, volumetric mapping using signed distance function submaps [J ] . IEEE Robotics and Automation Letters , 2020 , 5 ( 1 ): 227 - 234 .

CHANG Y , TIAN Y L , HOW J P , et al . Kimera-multi: a system for distributed multi-robot metric-semantic simultaneous localization and mapping [C ] // 2021 IEEE International Conference on Robotics and Automation (ICRA) . Piscataway : IEEE , 2021 : 11210 - 11218 .

BARTOLOMEI L , KARRER M , CHLI M . Multi-robot coordination with agent-server architecture for autonomous navigation in partially unknown environments [C ] // 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Piscataway : IEEE , 2020 : 1516 - 1522 .

LIU X Y , YE W C , TIAN C R , et al . Coxgraph: Multi-robot collaborative, globally consistent, online dense reconstruction system [C ] // 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Piscataway : IEEE , 2021 : 8722 - 8728 .

李西亮 . 基于子图的多机器人协同语义稠密建图方法的研究 [D ] . 杭州 : 浙江大学 , 2023 .

LI X L . Research on Multi-Robot Ccooperative Semantic Dense Mapping Method Based on Subgraph [D ] . Hangzhou : Zhejiang University , 2023 . (in Chinese)

BAI Y L , MIAO Z Q , WANG X K , et al . VDBblox: Accurate and efficient distance fields for path planning and mesh reconstruction [C ] // 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Piscataway : IEEE , 2023 : 7187 - 7194 .

KLEIN G , MURRAY D . Parallel tracking and mapping for small AR workspaces [C ] // 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality . Piscataway : IEEE , 2007 : 225 - 234 .

SONG S Y , CHANDRAKER M , GUEST C C . Parallel, real-time monocular visual odometry [C ] // 2013 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2013 : 4698 - 4705 .

MUR-ARTAL R , TARDÓS 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 .

WHELAN T , SALAS-MORENO R F , GLOCKER B , et al . ElasticFusion: Real-time dense SLAM and light source estimation [J ] . The International Journal of Robotics Research , 2016 , 35 ( 14 ): 1697 - 1716 .

DAI A , NIEßNER M , ZOLLHÖFER M , et al . BundleFusion [J ] . ACM Transactions on Graphics , 2017 , 36 ( 4 ): 1 .

SUN J M , XIE Y M , CHEN L H , et al . NeuralRecon: Real-time coherent 3D reconstruction from monocular video [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 15593 - 15602 .

RAJON D A , BOLCH W E . Marching cube algorithm: Review and trilinear interpolation adaptation for image-based dosimetric models [J ] . Computerized Medical Imaging and Graphics , 2003 , 27 ( 5 ): 411 - 435 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于自适应空间稀疏化的高效多视图立体匹配

动态遮挡场景下基于改进Transformer实例分割的VSLAM算法

光场相机三维重建研究进展与展望

基于改进关键帧选取策略的快速PL-SLAM算法