{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:36:24Z","timestamp":1777901784709,"version":"3.51.4"},"reference-count":48,"publisher":"American Institute of Aeronautics and Astronautics (AIAA)","issue":"5","funder":[{"name":"Anhui Provincial Science and Technology Innovation Tackling Plan","award":["S202523ay12050004"],"award-info":[{"award-number":["S202523ay12050004"]}]},{"name":"Xi\u2019an Xiangteng Microelectronics Technology Co., Ltd\/Innovation Fund Project","award":["XT-QC-202309-119278"],"award-info":[{"award-number":["XT-QC-202309-119278"]}]}],"content-domain":{"domain":["arc.aiaa.org"],"crossmark-restriction":true},"short-container-title":["Journal of Aerospace Information Systems"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:p>Vision-based instance-level semantic dense 3D reconstruction (ISDR) for satellite components can significantly enhance on-orbit service robots' perceptual capabilities for autonomous close-range tasks such as component repairs. However, existing ISDR methods, designed for ground scenarios, struggle with satellite targets' weak, repetitive textures and require GPU support, limiting their use on resource-constrained on-orbit platforms. To address these limitations, this paper proposes a lightweight method that builds on prior instance segmentation research. First, a pose estimation algorithm utilizing ORB and improved EDLine features achieves 40\u201370% higher tracking success rates on satellite flyby datasets compared to benchmarks. Second, the proposed lightweight dense 3D reconstruction method, optimized by accelerating truncated signed distance function fusion and surface extraction, achieves real-time performance at 23\u00a0Hz on a CPU with 5\u00a0mm voxel resolution. Third, by leveraging adjacent keyframe information, the instance-level semantic fusion improves efficiency by 77% over Voxblox++ at 5\u00a0mm resolution. Finally, the proposed ISDR method is validated on synthetic satellite fly-around datasets, achieving interactive-rate ISDR (10\u00a0Hz) on non-GPU platforms.<\/jats:p>","DOI":"10.2514\/1.i011693","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T05:37:08Z","timestamp":1770010628000},"page":"453-463","update-policy":"https:\/\/doi.org\/10.2514\/aiaa_crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Instance-Level Semantic Dense Three-Dimensional Reconstruction for Satellite Components"],"prefix":"10.2514","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-5729","authenticated-orcid":false,"given":"Qianlong","family":"Li","sequence":"first","affiliation":[{"name":"Chery Automobile Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanxia","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Fu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Xu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Jia","sequence":"additional","affiliation":[{"name":"Chery Automobile Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1387","reference":[{"key":"r1","doi-asserted-by":"crossref","unstructured":"ChenJ.WeiL.ZhaoG. \u201cAn Improved Lightweight Model Based on Mask R-CNN for Satellite Component Recognition,\u201d 2020 2nd International Conference on Industrial Artificial Intelligence (IAI), IEEE Publ., Piscataway, NJ, 2020, pp.\u00a01\u20136. 10.1109\/IAI50351.2020.9262224","DOI":"10.1109\/IAI50351.2020.9262224"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.11.002"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.14733\/cadaps.2021.1359-1372"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2923960"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146502"},{"key":"r6","doi-asserted-by":"crossref","unstructured":"MccormacJ.ClarkR.BloeschM.DavisonA.LeuteneggerS. \u201cFusion++: Volumetric Object-Level SLAM,\u201d 2018 International Conference on 3D Vision (3DV), IEEE Publ., Piscataway, NJ, 2018, pp.\u00a032\u201341. 10.1109\/3DV.2018.00015","DOI":"10.1109\/3DV.2018.00015"},{"key":"r7","first-page":"1","volume":"2020","author":"Li W.","year":"2020","journal-title":"Discrete Dynamics in Nature and Society"},{"key":"r8","doi-asserted-by":"crossref","unstructured":"RunzM.BuffierM.AgapitoL. \u201cMaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects,\u201d 2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Inst. of Electrical and Electronics Engineers, New York, 2018, pp.\u00a010\u201320. 10.1109\/ISMAR.2018.00024","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"r9","doi-asserted-by":"crossref","unstructured":"NaritaG.SenoT.IshikawaT.KajiY. \u201cPanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things,\u201d 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE Publ., Piscataway, NJ, 2019, pp.\u00a04205\u20134212. 10.1109\/IROS40897.2019.8967890","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2023.01.007"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"r12","doi-asserted-by":"crossref","unstructured":"DorM.TsiotrasP. \u201cORB-SLAM Applied to Spacecraft Non-Cooperative Rendezvous,\u201d 2018 Space Flight Mechanics Meeting, AIAA Paper 2018-1963, 2018. 10.2514\/6.2018-1963","DOI":"10.2514\/6.2018-1963"},{"key":"r13","doi-asserted-by":"crossref","unstructured":"ThomasD.KellyS.BlackJ. \u201cA Monocular SLAM Method for Satellite Proximity Operations,\u201d 2016 American Control Conference (ACC), IEEE Publ., Piscataway, NJ, 2016, pp.\u00a04035\u20134040. 10.1109\/ACC.2016.7525555","DOI":"10.1109\/ACC.2016.7525555"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"r15","doi-asserted-by":"crossref","unstructured":"QuC.ShivakumarS. S.MillerI. D.TaylorC. J. \u201cDSOL: A Fast Direct Sparse Odometry Scheme,\u201d 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE Publ., Piscataway, NJ, 2022, pp.\u00a010,587\u201310,594. 10.1109\/IROS47612.2022.9981491","DOI":"10.1109\/IROS47612.2022.9981491"},{"key":"r16","doi-asserted-by":"crossref","unstructured":"NewcombeR. A.LovegroveS. J.DavisonA. J. \u201cDTAM: Dense Tracking and Mapping in Real-Time,\u201d 2011 IEEE International Conference on Computer Vision (ICCV), Inst. of Electrical and Electronics Engineers, New York, 2011, pp.\u00a02320\u20132327. 10.1109\/ICCV.2011.6126513","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2009.11.022"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2017.03.008"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3036868"},{"key":"r20","doi-asserted-by":"crossref","unstructured":"YunusR.LiY.TombariF. \u201cManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames,\u201d 2021 IEEE International Conference on Robotics and Automation (ICRA), Inst. of Electrical and Electronics Engineers, New York, 2021, pp.\u00a06687\u20136693. 10.1109\/ICRA48506.2021.9562030","DOI":"10.1109\/ICRA48506.2021.9562030"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01103-0"},{"key":"r22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3015456"},{"key":"r23","doi-asserted-by":"crossref","unstructured":"PumarolaA.VakhitovA.AgudoA.SanfeliuA.Moreno-NoguerF. \u201cPL-SLAM: Real-Time Monocular Visual SLAM with Points and Lines,\u201d 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017, pp.\u00a04503\u20134508. 10.1109\/ICRA.2017.7989522","DOI":"10.1109\/ICRA.2017.7989522"},{"key":"r24","doi-asserted-by":"crossref","unstructured":"ChenZ.ZhangC.SuD.WangS. \u201c3D Reconstruction of Spatial Non Cooperative Target Based on Improved Traditional Algorithm,\u201d 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence, Assoc. for Computing Machinery, New York, 2021, pp.\u00a01\u20136. 10.1145\/3508546.3508578","DOI":"10.1145\/3508546.3508578"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6940"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_33"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.3390\/rs15174163"},{"key":"r28","unstructured":"TosiF.ZhangY.GongZ.Sandstr\u00f6mE.MattocciaS.OswaldM. R.PoggiM. \u201cHow NeRFs and 3D Gaussian Splatting are Reshaping SLAM: A Survey,\u201d ArXiv, 2024, pp.\u00a01\u201325. 10.48550\/arXiv.2402.13255"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3249661"},{"key":"r30","doi-asserted-by":"crossref","unstructured":"SchopsT.SattlerT.PollefeysM. \u201cBAD SLAM: Bundle Adjusted Direct RGB-D SLAM,\u201d 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Publ., Piscataway, NJ, 2019, pp.\u00a0134\u2013144. 10.1109\/CVPR.2019.00022","DOI":"10.1109\/CVPR.2019.00022"},{"key":"r31","first-page":"1","volume":"2018","author":"Han L.","year":"2018","journal-title":"Robotics: Science and Systems"},{"key":"r32","doi-asserted-by":"publisher","DOI":"10.3390\/rs14040979"},{"key":"r33","first-page":"1","volume":"72","author":"Lu J.","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"r34","doi-asserted-by":"crossref","unstructured":"AkinlarC.TopalC. \u201cEdlines: Real-Time Line Segment Detection by Edge Drawing Ed,\u201d 2011 18th IEEE International Conference on Image Processing (ICIP 2011), Inst. of Electrical and Electronics Engineers, New York, 2011, pp.\u00a02837\u20132840. 10.1109\/ICIP.2011.6116138","DOI":"10.1109\/ICIP.2011.6116138"},{"key":"r35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.300"},{"key":"r36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108619"},{"key":"r37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.05.006"},{"issue":"4","key":"r38","first-page":"1","volume":"4","author":"Klingensmith M.","year":"2015","journal-title":"Robotics: Science and Systems"},{"key":"r39","doi-asserted-by":"publisher","DOI":"10.3390\/rs14040979"},{"key":"r40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01578"},{"key":"r41","doi-asserted-by":"crossref","unstructured":"NguyenC. V.IzadiS.LovellD. \u201cModeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking,\u201d 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), IEEE Publ., Piscataway, NJ, 2012, pp.\u00a0524\u2013530. 10.1109\/3DIMPVT.2012.84","DOI":"10.1109\/3DIMPVT.2012.84"},{"key":"r42","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02139-w"},{"key":"r43","doi-asserted-by":"publisher","DOI":"10.3390\/app12041792"},{"key":"r44","doi-asserted-by":"crossref","unstructured":"HandaA.WhelanT.McDonaldJ.DavisonA. J. \u201cA Benchmark for RGB-D Visual Odometry, 3D Reconstruction and SLAM,\u201d 2014 IEEE International Conference on Robotics and Automation (ICRA), Inst. of Electrical and Electronics Engineers, New York, 2014, pp.\u00a01524\u20131531. 10.1109\/ICRA.2014.6907054","DOI":"10.1109\/ICRA.2014.6907054"},{"key":"r45","doi-asserted-by":"crossref","unstructured":"SturmJ.EngelhardN.EndresF.BurgardW.CremersD. \u201cA Benchmark for the Evaluation of RGB-D SLAM Systems,\u201d 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS. 2012), IEEE Publ., Piscataway, NJ, 2012, pp.\u00a0573\u2013580. 10.1109\/IROS.2012.6385773","DOI":"10.1109\/IROS.2012.6385773"},{"key":"r46","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916669237"},{"key":"r47","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3054739"},{"key":"r48","doi-asserted-by":"crossref","unstructured":"OleynikovaH.TaylorZ.FehrM.SiegwartR.NietoJ. \u201cVoxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning,\u201d 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE Publ., Piscataway, NJ, 2017, pp.\u00a01366\u20131373. 10.1109\/IROS.2017.8202315","DOI":"10.1109\/IROS.2017.8202315"}],"container-title":["Journal of Aerospace Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/arc.aiaa.org\/doi\/pdf\/10.2514\/1.I011693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:10:11Z","timestamp":1777633811000},"score":1,"resource":{"primary":{"URL":"https:\/\/arc.aiaa.org\/doi\/10.2514\/1.I011693"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.2514\/1.I011693"],"URL":"https:\/\/doi.org\/10.2514\/1.i011693","relation":{},"ISSN":["1940-3151","2327-3097"],"issn-type":[{"value":"1940-3151","type":"print"},{"value":"2327-3097","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2025-05-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}