中国移动通信集团设计院有限公司,北京 100080
[ "邢小刚(1977- ),男,中国移动通信集团设计院有限公司高级工程师,主要研究方向为5G无线通信算法及数字孪生建模。" ]
[ "李梦宇(1993- ),男,中国移动通信集团设计院有限公司工程师,主要研究方向为5G无线通信算法及人工智能技术。" ]
[ "徐玉波(1980- ),男,中国移动通信集团设计院有限公司工程师,主要研究方向为5G无线通信组网规划及数字孪生建模。" ]
[ "刁兆坤(1972- ),男,中国移动通信集团设计院有限公司高级工程师,主要研究方向5G通信行业规划、设计、优化及5G-Advanced低空经济等。" ]
[ "李洲(1988- ),男,中国移动通信集团设计院有限公司高级工程师,主要研究方向为5G/5G-Advanced无线通信组网规划部署及关键技术产品。" ]
收稿:2025-01-13,
修回:2025-07-03,
录用:2025-10-15,
纸质出版:2026-02-20
移动端阅览
邢小刚,李梦宇,徐玉波等.基于SfM及SOLO算法的通信机房智能三维建模技术方案研究[J].电信科学,2026,42(02):204-212.
Xing Xiaogang,Li Mengyu,Xu Yubo,et al.Research on intelligent 3D modeling technology scheme for telecommunication equipment rooms based on SfM and SOLO algorithms[J].Telecommunications Science,2026,42(02):204-212.
邢小刚,李梦宇,徐玉波等.基于SfM及SOLO算法的通信机房智能三维建模技术方案研究[J].电信科学,2026,42(02):204-212. DOI: 10.11959/j.issn.1000-0801.2026030.
Xing Xiaogang,Li Mengyu,Xu Yubo,et al.Research on intelligent 3D modeling technology scheme for telecommunication equipment rooms based on SfM and SOLO algorithms[J].Telecommunications Science,2026,42(02):204-212. DOI: 10.11959/j.issn.1000-0801.2026030.
建设通信机房的数字孪生系统,对提升通信网络主要资产的管理水平具有重要意义。机房设备、设施的低成本、高质量三维建模是数字孪生系统建设的关键。为此,提出了一种通信机房的智能三维建模技术方案,依靠普通相机采集的多角度照片组,综合运用人工智能(artificial intelligence,AI)技术,可生成机房设备、设施的高精度、带语义三维模型。该方案联合使用运动恢复结构(structure from motion,SfM)及按位置分割对象(segmenting objects by locations,SOLO)算法,优化了SOLO算法的损失函数。分析表明,该方案可显著提升识别准确度,同时提升了建模运算效率,降低了建模需要采集的现场照片数量和精度要求,具有很强的实用性。
The establishment of a digital twin system for communication equipment rooms holds substantial significance in elevating the management level of communication networks and assets. Central to this endeavor is the low-cost yet high-quality three-dimensional modeling of the equipment and facilities within the rooms. For this reason
an intelligent 3D modeling framework for telecommunication equipment rooms was devised
whereby
leveraging multi-angle photographs captured by ordinary cameras and integrating advanced artificial intelligence (AI) technology
high-precision
semantically rich three-dimensional models of the equipment and facilities could be generated. This solution incorporated the structure from motion (SfM) and segmenting objects by locations (SOLO) algorithms
with the loss function of the SOLO algorithm being optimized. Experimental results demonstrate that this approach markedly enhances recognition accuracy
substantially boosts modeling efficiency
and effectively reduces the requisite quantity and precision threshold of photographs
thereby manifesting robust practicality.
刘咏荷 , 邢小刚 , 徐玉波 , 等 . 三维勘测建模技术研究及通信行业应用评估 [J ] . 电信工程技术与标准化 , 2023 , 36 ( 8 ): 36 - 42 .
Liu Y H , Xing X G , Xu Y B , et al . Research on 3D survey modeling technology and application evaluation in the communication industry [J ] . Telecom Engineering Technics and Standardization , 2023 , 36 ( 8 ): 36 - 42 .
王云舒 , 刘建业 , 曾庆化 , 等 . 结构光辅助的惯性/视觉室内导航三维环境重构方法 [J ] . 中国惯性技术学报 , 2016 , 24 ( 1 ): 51 - 58 .
Wang Y S , Liu J Y , Zeng Q H , et al . 3D environment restructure method with structured light for indoor vision/inertial navigation [J ] . Journal of Chinese Inertial Technology , 2016 , 24 ( 1 ): 51 - 58 .
郑太雄 , 黄帅 , 李永福 , 等 . 基于视觉的三维重建关键技术研究综述 [J ] . 自动化学报 , 2020 , 46 ( 4 ): 631 - 652 .
Zheng T X , Huang S , Li Y F , et al . Key techniques for vision based 3D reconstruction: a review [J ] . Acta Automatica Sinica , 2020 , 46 ( 4 ): 631 - 652 .
徐凯 , 胡瑞珍 , 杨鑫 . 几何引导的主动式三维感知与交互 [J ] . 图学学报 , 2022 , 43 ( 6 ): 1049 - 1056 .
Xu K , Hu R Z , Yang X . Geometry-guided active 3D perception and interaction [J ] . Journal of Graphics , 2022 , 43 ( 6 ): 1049 - 1056 .
曲熠 , 陈莹 . 基于尺度线索增强的无监督单目深度估计 [J ] . 电子学报 , 2024 , 52 ( 9 ): 3217 - 3227 .
Qu Y , Chen Y . Unsupervised monocular depth estimation based on scale clue enhancement [J ] . Acta Electronica Sinica , 2024 , 52 ( 9 ): 3217 - 3227 .
娄宁 , 马健 , 杨永崇 , 等 . 倾斜摄影的单体精细化三维建模技术 [J ] . 遥感信息 , 2020 , 35 ( 6 ): 44 - 48 .
Lou N , Ma J , Yang Y C , et al . Monolithic 3D modeling technology for tilting photography [J ] . Remote Sensing Information , 2020 , 35 ( 6 ): 44 - 48 .
刘欣怡 , 张永军 , 范伟伟 , 等 . 无人机倾斜摄影三维建模技术研究现状及展望 [J ] . 时空信息学报 , 2023 , 30 ( 1 ): 41 - 48 .
Liu X Y , Zhang Y J , Fan W W , et al . 3D modeling based on UAV oblique photogrammetry: Research status and prospect [J ] . Journal of Spatio-Temporal Information , 2023 , 30 ( 1 ): 41 - 48 .
刘双童 , 王明孝 . 基于倾斜摄影建模技术的三维地形实体模型制作研究 [J ] . 测绘与空间地理信息 , 2019 , 42 ( 1 ): 31 - 33 .
Liu S T , Wang M X . Research on 3D terrain solid model production based on tilting photography modeling technology [J ] . Geomatics & Spatial Information Technology , 2019 , 42 ( 1 ): 31 - 33 .
Wang H , Ding L , Dong S , et al . CAGroup3D: class-aware grouping for 3D object detection on point clouds [J ] . Advances in Neural Information Processing Systems , 2022 , 35 : 8 .
师春艳 . 基于三维视觉的室内设计虚拟现实方法研究 [J ] . 现代电子技术 , 2018 , 41 ( 5 ): 78 - 82, 88 .
Shi C Y . Research on virtual reality method of indoor design based on 3D vision [J ] . Modern Electronics Technique , 2018 , 41 ( 5 ): 78 - 82, 88 .
欧元汉 , 刘进 , 劳冬影 . 基于MVS点云的城市建筑三维重建方法 [J ] . 计算机工程与设计 , 2015 , 36 ( 11 ): 3064 - 3068 .
Ou Y H , Liu J , Lao D Y . 3D reconstruction method of city buildings based on MVS point cloud [J ] . Computer Engineering and Design , 2015 , 36 ( 11 ): 3064 - 3068 .
张彦雯 , 胡凯 , 王鹏盛 . 三维重建算法研究综述 [J ] . 南京信息工程大学学报 , 2020 , 12 ( 5 ): 591 - 602 .
Zhang Y W , Hu K , Wang P S . Review of 3D reconstruction algorithms [J ] . Journal of Nanjing University of Information Science & Technology , 2020 , 12 ( 5 ): 591 - 602 .
Wang X L , Kong T , Shen C H , et al . SOLO: segmenting objects by locations [M ] // Computer Vision-ECCV 2020 . Cham : Springer International Publishing , 2020 : 649 - 665 .
He K M , Gkioxari G , DolláR P , et al . Mask R-CNN [C ] // Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2017 : 2980 - 2988 .
Lin T Y , Goyal P , Girshick R , et al . Focal loss for dense object detection [C ] // Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2017 : 2999 - 3007 .
0
浏览量
38
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621