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.
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.
Research on intelligent 3D modeling technology scheme for telecommunication equipment rooms based on SfM and SOLO algorithms
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。
Abstract
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
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 .
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 .
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 .
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 .
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 .
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 .
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 .
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 .