Enhancing lidar data processing for advanced building facade segmentation and 3D reconstruction

국문 초록 (Abstract)

본 연구는 LiDAR 데이터의 방사량 정보가 건물 facade 구성 요소에 대한 정밀한 평가 및 인식에 미치는 영향에 대해 분석하하고, 이를 통해 3D 재구성 모델의 정확도를 향상시키자 하 였으며, 건축 공학 및 건설 산업의 능력을 강화하기 위한 포괄적인 방법이 제시하였다. LiDAR 계측로부터 얻은 방사량 정보는 입사각 및 거리와 같은 기하학적 요소에 대한 경험적인 접근 을 사용하여 보정하였다. 본 연구에서는 강도 데이터에 대한 경험적 보정 모델을 개발하고, 건물 facade 데이터를 적용하여 정확한 세분화를 수행하고 기하학 및 텍스처 분석을 위한 3D 재구성 모델을 생성하였다.

제안된 방법을 통해 입사각 및 거리가 intensity에 미치는 영향을 효과적으로 감소시키고 균질한 표면에서 나타날 수 있는 변수를 줄이고자 하였다. 3D 포인트 클라우드 및 방사량 정보를 활용하여 건물 facade 구성 요소를 정확하게 세분화함으로써 건축 유지 보수, 도시 계획을 효과적으로 수행할 수 있다. facade 구성 요소의 정확한 식별을 통해 물리적 상태, 에너지 효율에 대한 실시간 평가를 가능하게 한다. 본 논문에서 제안하는 방법을 디지털 트 윈에 적용하면 대상 건물에 대한 지속적인 모니터링, 적극적인 유지 보수 및 성능 최적화가 가능하다.

이후 facade 세분화 결과를 기반으로 성능이 향상된 3D 모델을 재구성하였다. 본 논문에 서는 건물 facade를 재구성하기 위해 3D Hough 변환 기술을 사용하여 더 높은 성능의 기하학 및 텍스처 분석을 가능캐하였다. 재구성된 3D 모델에서 파생된 결과물과 텍스처 및 기하학 분석은 구조 평가, 설계 검증, 유지 보수 계획 및 품질 보증에서 중요한 역할을 한다.

AEC 산업은 보정된 LiDAR intensity 데이터를 활용하여 건물 평가 및 유지보수에 대한 종합적인 접근 방식의 이점을 누릴 수 있다. 정확한 건물 외관 세분화는 전반적인 상태에 대한 통찰력을 제공하며, 견고한 3D 재구성 및 파사드 분석은 물리적 구조의 정확하고 상세한 표 현을 보증하여 가상 현실, 도시 계획 및 건축 설계와 같은 응용 프로그램을 지원한다. 이러한 기술을 디지털 트윈 프레임워크에 통합하면 건물 성능의 모니터링, 분석 및 예측을 강화하여 안전성, 지속 가능성 및 효율성을 위한 적극적인 조치를 가능하게 한다.

다국어 초록 (Multilingual Abstract)

This study focuses on the pivotal role of radiometric information in Light Detection and Ranging(LiDAR) data for precise assessment and recognition of building facade components, thereby enhancing the accuracy of Three Dimensional(3D) reconstruction models. A comprehensive approach is presented to augment the capabilities of the architectural engineering and construction (AEC) industry. Radiometric information obtained from LiDAR technology is corrected using an empirical approach to address geometric factors like incidence angle and range. The study involves developing an empirical correction model for intensity data, applying it to building facade data for accurate segmentation, and creating a 3D reconstructed model for geometric and texture analysis.

The proposed method effectively mitigates the influence of incidence angle and distance on intensity values, reducing variations on homogeneous surfaces. Leveraging 3D point clouds and radiometric information enables precise segmentation of building facade components, offering insights for building maintenance, urban planning, and security. Accurate identification of facade components allows real-time assessment of physical condition, energy efficiency, and aesthetic value. Incorporating this method into a digital twin facilitates continuous monitoring, proactive maintenance, and performance optimization.

Subsequently, a 3D reconstructed model is crafted from the segmented results of the facade. The study employs a 3D Hough transform technique to reconstruct the building facade, facilitating geometric and texture analyses. The outputs derived from the 3D reconstruction model, as well as the texture and geometric analyses, play a pivotal role in structural assessment, design verification, maintenance planning, and quality assurance.

Utilizing corrected LiDAR intensity data, the AEC industry benefits from a holistic approach to building assessment and maintenance. Accurate building facade segmentation provides insights into overall condition, while robust 3D reconstruction and facade analysis ensure an accurate and detailed representation of physical structures, supporting applications such as virtual reality, urban planning, and architectural design. Integrating these technologies into digital twin frameworks enhances monitoring, analysis, and prediction of building performance, enabling proactive measures for safety, sustainability, and efficiency.

목차 (Table of Contents)

• 1 Introduction 1
• 1.1 Background 1
• 1.2 Overview of the Principle of LiDAR Measurement 3
• 1.3 Research Trends 6
• 1.4 Problem Statement 13
• 1.5 Research Objectives 14
• 1.6 Scope and Limitations 15
• 2 Correction of Lidar Intensity 17
• 2.1 Overview 17
• 2.2 Development of empirical intensity correction model 19
• 2.3 Experimental Study 22
• 2.4 Validation Result 25
• 2.5 Summary 32
• 3 Automatic segmentation of building facade based on the corrected radiometric information of pointcloud 35
• 3.1 Overview 35
• 3.2 Experimental Study 38
• 3.3 Development of automated 2D building facade component segmentation technique 39
• 3.4 Development of automated 3D building facade components segmentation technique 56
• 3.5 Summary 65
• 4 3D Reconstruction and Analysis of Building Facades 67
• 4.1 Overview 67
• 4.2 Facade component detection and reconstruction 69
• 4.3 Geometry and texture analysis 82
• 4.4 summary 101
• 5 Conclusion 105
• References 111
• 초 록 127

참고문헌 (Reference)

1. Finding tiny faces, Deva Ramanan, Peiyun Hu and, In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 951–959, , 2017

2. Pyramid scene parsing network, Xiaojuan Qi, Jianping Shi, Jiaya Jia, Hengshuang Zhao, Xiaogang Wang and, In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, , 2017

3. Terrestrial laser scanning In, Mathias Lemmens, Geoinformation, pages 101–121 Springer, , 2011

4. Hierarchical clustering schemes, Stephen C Johnson, Psychometrika, 32(3):241–254, , 1967

5. Randomized hough transform (rht), Lei Xu and, Erkki Oja, Pekka Kultanen, In Proceedings. 10th International Conference on Pattern Recognition, volume 1, pages 631–635. IEEE, , 1990

6. Learning what and where to transfer, Hankook Lee, Yunhun Jang, Jinwoo Shin, Sung Ju Hwang and, In International conference on machine learning, pages 3030–3039. PMLR, , 2019

7. Airborne and terrestrial laser scanning, George Vosselman and, HansGerd Maas, CRC press, , 2010

8. Deep residual learning for image recognition, Jian Sun, Shaoqing Ren and, Kaiming He, Xiangyu Zhang, In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, , 2016

9. Dynamic graph cnn for learning on point clouds, Sanjay E Sarma, Michael M Bronstein and, Ziwei Liu, Justin M Solomon, Yue Wang, Yongbin Sun, Acm Transactions On Graphics (tog), 38(5):1–12, , 2019

10. Algorithm as 136: A kmeans clustering algorithm, Manchek A Wong, John A Hartigan and, Journal of the royal statistical society. series c (applied statistics) 28(1):100–108, , 1979

11. Transfer learning in natural language processing, Matthew E Peters, Sebastian Ruder, Thomas Wolf, Swabha Swayamdipta and, In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Tutorials, pages 15–18, , 2019

12. A survey on the weierstrass approximation theorem, Dilcia P´erez and, Yamilet Quintana, arXiv preprint math/0611038, , 2006

13. Method and means for recognizing complex patterns, Paul VC Hough, 3,069,654, , 1962

14. 2d3d fusion for layer decomposition of urban facades, Baoquan Chen and, Niloy J. Mitra, Daniel CohenOr, Andrei Sharf, Qian Zheng, Yangyan Li, In 2011 International Conference on Computer Vision. IEEE, , 2011

15. Potree: Rendering large point clouds in web browsers, Markus Sch¨utz et al, Technische Universit¨at Wien, Wiede´n, , 2016

16. Computer visionbased construction progress monitoring, Varun Kumar Reja, Quang Phuc Ha, Koshy Varghese and, Automation in Construction, 138:104245, , 2022

17. 3d preservation of buildings–reconstructing the past, Michael Klein, Dieter Fritsch and, Multimedia Tools and Applications, 77:9153–9170, , 2018

18. Morphological segmentation of building fa¸cade images, Beatriz Marcotegui, Jorge Hern´andez and, In 2009 16th IEEE International Conference on Image Processing (ICIP), pages 4029–4032. IEEE, , 2009

19. Quantifying the influence of rain in lidar performance, Susana Lag¨uela, Pedro Arias, L D´ıazVilari˜no and, H Gonz´alezJorge, A Filgueira, Measurement, 95:143–148, , 2017

20. Tls for detecting small damages on a building fa¸cade, D Costantino, A Masiero and, ISPRS ANNALS OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES, 42:831–836, , 2019

21. 3d building fa¸cade reconstruction using deep learning, Froso Sarri and, Konstantinos Bacharidis, Lemonia Ragia, ISPRS International Journal of GeoInformation, 9(5):322, , 2020

22. Hyperspectral 3d point cloud segmentation using randlanet, Felix Igelbrink and, Isaak Mitschke, Thomas Wiemann, Joachim Hertzberg, In Intelligent Autonomous Systems 17: Proceedings of the 17th International Conference IAS17, pages 301– 312. Springer, 2023, , 2023

23. Literature review of industry 4.0 and related technologies, Samet Gursev, Ercan Oztemel and, 31:127–182, , 2020

24. Pdebased 3d surface reconstruction from multiview 2d images, Lihua You and, Liqi Zhou, Zaiping Zhu, Jianjun Zhang, Andres Iglesias, 10(4):542, , 2022

25. A concise survey for 3d reconstruction of building fa¸cades, Ebroul Izquierdo, Patrycia Klavdianos, Qianni Zhang and, In 2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), pages 1–4. IEEE, , 2013

26. Line detection in images through regularized hough transform, W Clem Karl, Nitin Aggarwal and, IEEE transactions on image processing, 15(3):582–591, , 2006

27. A twoview based multilayer feature graph for robot navigation, Dezhen Song, Haifeng Li, Jingtai Liu, Yan Lu and, In 2012 IEEE International Conference on Robotics and Automation, pages 3580–3587. IEEE, , 2012

28. Multimodal 3d facade reconstruction using 3d lidar and images, Patrice Jean Delmas, Haotian Xu, Trevor Edwin Gee and, ChiaYen Chen, Wannes van der Mark, In Image and Video Technology: 9th PacificRim Symposium, PSIVT 2019, Sydney, NSW, Australia Proceedings 9, pages 281–295. Springer, , 2019

29. U-netConvolutional networks for biomedical image segmentation, Olaf Ronneberger, Philipp Fischer and, Thomas Brox, In Medical Image Computing and ComputerAssisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, Proceedings, Part III 18, pages 234–241. Springer, , 2015

30. On the curvature of curves and surfaces defined by normalforms, Erich Hartmann, Computer Aided Geometric Design, 16(5):355–376, , 1999

31. A survey on hough transform, theory, techniques and applications, Mohamed Sameer and, Sherien Mohammad, Mohammad Ehab Ragab, Allam Shehata Hassanein, arXiv preprint arXiv:1502.02160, , 2015

32. Tls field data based intensity correction for forest environments, MO Huber, J Heinzel and, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 41:643–649, , 2016

33. Automatic building exterior mapping using multilayer feature graphs, Yan Lu, Yiliang Xu, Dezhen Song, Sangmin Oh, AG Amitha Perera and, In 2013 IEEE International Conference on Automation Science and Engineering (CASE), pages 162–167. IEEE, , 2013

34. Geomatics for smart citiesconcept, key techniques, and applications, Deren Li, Xiran Zhou and, Jie Shan, Yuan Yao, Zhenfeng Shao, Geospatial Information Science, 16(1):13–24, , 2013

35. Point cloud intensity correction for 2d lidar mobile laser scanning, Xuefeng Wei, Qiujie Li, Youlin Xu and, Xu Liu, Wireless Communications and Mobile Computing, 2022:1–22, , 2022

36. Analysis of full waveform lidar data for tree species classification, Uwe Stilla, Peter Krzystek and, Josef Reitberger, International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 36(Part 3):228–233, , 2006

37. Effect of incidence angle on laser scanner intensity and surface data, Sanna Kaasalainen and, Antero Kukko, Paula Litkey, 47(7):986–992, , 2008

38. Topographic and distance effects in laser scanner intensity correction, A Vain, A Kukko, A Krooks and, S Kaasalainen, Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci, 38(3/W8):219–222, , 2009

39. 3d facade reconstruction using the fusion of images and lidar: A review, ChiaYen Chen, Haotian Xu and, In New Trends in Computer Technologies and Applications: 23rd International Computer Symposium, ICS 2018, Yunlin, Taiwan, Revised Selected Papers 23, pages 178–185. Springer, , 2018

40. Parametric asbuilt model generation of complex shapes from point clouds, Luigi Barazzetti, Advanced Engineering Informatics, 30(3):298–311, , 2016

41. Physicallybased rendering of animated point clouds for extended reality, Marco Gribaudo and, Pietro Pi azzolla, Giorgio Colombo, Matteo Pozzi, Marco Rossoni, pages 1–9, 2023, , 2023

42. Beam deflection monitoring based on a genetic algorithm using lidar data, Donghwan Lee, Michael Bekele Maru, Gichun Cha and, Seunghee Park, 20(7):2144, , 2020

43. Transfer learning in computer vision tasks: Remember where you come from, Yin Cui, YiHsuan Tsai and, Serge Belongie, Hang Zhang, Xuhong Li, Jingchun Cheng, Franck Davoine, Yves Grandvalet, MingHsuan Yang, 93:103853, , 2020

44. Cnnbased 3d object classification using hough space of lidar point clouds, Jinming Liu and, Wei Song, Yifei Tian, Simon Fong, Lingfeng Zhang, Amanda Gozho, Humancentric Computing and Information Sciences, 10:1–14, , 2020

45. Continuous plane detection in pointcloud data based on 3d hough transform, Michal Spanel, Pavel Smrz and, Zdenek Materna, Rostislav Hulik, 25(1):86–97, , 2014

46. Digital twin application in the construction industry: A literature review, DeGraft Joe Opoku, Maria Rashidi, Robert OseiKyei and, Srinath Perera, 40:102726, , 2021

47. PointnetDeep learning on point sets for 3d classification and segmentation, Kaichun Mo and, Hao Su, Charles R Qi, Leonidas J Guibas, In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, , 2017

48. Slicing method for curved fa¸cade and window extraction from point clouds, Debra F. Laefer, S. M. Iman Zolanvari and, 119:334–346, , 2016

49. Radiometric calibration of a dualwavelength, fullwaveform terrestrial lidar, Glenn Howe, Supriya Chakrabarti, Ewan S Douglas, Crystal B Schaaf, Kuravi Hewawasam, David LB Jupp, Timothy A Cook, Alan H Strahler, Ian Paynter et al, Zhan Li, 16(3):313, , 2016

50. Automated bridge component recognition from point clouds using deep learning, SungHan Sim, Jinyoung Yoon and, Hyunjun Kim, 27(9):e2591, , 2020

51. Correction of laser scanning intensity data: Data and modeldriven approaches, Norbert Pfeifer, Bernhard H¨ofle and, 62(6):415–433, , 2007

52. Analysis of building textures for reconstructing partially occluded facades In, Christopher Rasmussen, Thommen Korah and, Computer Vision–ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, Proceedings, Part I 10, pages 359–372. Springer, , 2008

53. Discovering repetitive patterns in facade images using a RANSACstyle algorithm, Kiyoshi Honda and, Matthew Dailey, Masahiko Nagai, Kumpee Teeravech, ISPRS Journal of Photogrammetry and Remote Sensing 92:38–53, , 2014

54. Learning semantic segmentation of largescale point clouds with random sampling, Bo Yang, Andrew Markham, Yulan Guo, Stefano Rosa, Linhai Xie, Zhihua Wang, Niki Trigoni and, Qingyong Hu, 44(11):8338–8354, , 2021

55. Advances in computer visionbased civil infrastructure inspection and monitoring, Yasutaka Narazaki, Vedhus Hoskere and, Billie F Spencer Jr, Engineering, 5(2):199– 222, , 2019

56. Integration of the structural project into the bim paradigm: A literature review, V´ıctor Yepes, V´ıctor Fern´andezMora, Ignacio J Navarro and, 53:104318, , 2022

57. Normalization of lidar intensity data based on range and surface incidence angle, H Gross, Boris Jutzi and, 38:213–218, , 2009

58. Adaptive parameter tuning for morphological segmentation of building facade images, Andr´es Serna, Jorge Hern´andez and, Beatriz Marcotegui, In 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO), pages 2268–2272. IEEE, , 2012

59. Radiometric calibration of terrestrial laser scanners with external reference targets, Anssi Krooks, Harri Kaartinen, Antero Kukko and, Sanna Kaasalainen, 1(3):144–158, , 2009

60. Characterizing building materials using multispectral imagery and lidar intensity data, Aoife Gowen, Zohreh Zahiri, Debra F Laefer and, 44:102603, , 2021

61. Combination of overlapdriven adjustment and phong model for lidar intensity correction, Qiong Ding, Guoxiang Liu, Bruce King, Yanxiong Liu and, Wu Chen, 75:40–47, , 2013

62. Lidar inertial odometry aided robust lidar localization system in changing city scenes, Shenhua Hou, Shiyu Song, Guowei Wan and, Hang Gao, Wendong Ding, In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 4322–4328. IEEE, , 2020

63. Bimbased method to inform operation and maintenance phases through a simplified procedure, Massimiliano Condotta and, Chiara Scanagatta, 65:105730, 2023, , 2023

64. Glacier surface segmentation using airborne laser scanning point cloud and intensity data, Martin Rutzinger and, Norbert Pfeifer, Bernhard H¨ofle, Thomas Geist, International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 36(Part 3):W52, , 2007

65. Vanishing points detection using combination of fast hough transform and deep learning In, Alexander Sheshkus, Anastasia Ingacheva and, Dmitry Nikolaev, Tenth International Conference on Machine Vision (ICMV 2017), volume 10696, pages 101–108. SPIE, , 2018

66. Analysis and correction of the dependency between laser scanner intensity values and range, Danilo Schneider, Robert Blaskow and, The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(5):107, , 2014

67. Planar building facade segmentation and mapping using appearance and geometric constraints, Dezhen Song, Joseph Lee, Yan Lu and, In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, , 2014

68. A graphbased approach for 3d building model reconstruction from airborne lidar point clouds, Weiqing Mao and, Bin Wu, Feng Zhao, Qiusheng Wu, Jianping Wu, Shenjun Yao, Bailang Yu, 9(1):92, , 2017

69. Design and evaluation of a realworld virtual environment for architecture and urban planning, George Drettakis, Maria Roussou, Alex Reche and, Nicolas Tsingos, presence: teleoperators and virtual environments, 16(3):318–332, , 2007

70. Research on bridge deck health assessment system based on bim and computer vision technology, Yaowen Chen, Zhixin Qian, Yuxiang Li and, In Journal of Physics: Conference Series, volume 1802, page 042047. IOP Publishing, , 2021

71. Threedimensional building fa¸cade segmentation and opening area detection from point clouds, Atteyeh S. Natanzi, Debra F. Laefer and, S. M. Iman Zolanvari, 143:134–149, , 2018

72. Intensity data correction based on incidence angle and distance for terrestrial laser scanner, Kai Tan and, Xiaojun Cheng, 9(1):094094–094094, , 2015

73. Adaptive densitybased spatial clustering of applications with noise (dbscan) according to data, YiLeh Wu, WeiTung Wang, MawKae Hor, ChengYuan Tang and, In 2015 International Conference on Machine Learning and Cybernetics (ICMLC), volume 1, pages 445–451. IEEE, , 2015

74. Radiometric correction of laser scanning intensity data applied for terrestrial laser scanning, El Mustapha Mouaddib and, Nathan SanchizViel, Estelle Bretagne, Pascal Dassonvalle, 172:1–16, , 2021

75. Robust line detection in images of building facades using regionbased weighted hough transform, Nikolaos Vassilas and, Theocharis Tsenoglou, Djamchid Ghazanfarpour, In 2012 16th Panhellenic Conference on Informatics. IEEE, , 2012

76. 3d point cloud compression using conventional image compression for efficient data transmission, Hamidreza Houshiar and, Andreas N¨uchter, In 2015 XXV International Conference on Information, Communication and Automation Technologies (ICAT), pages 1–8. IEEE, , 2015

77. Discrimination between marls and limestones using intensity data from terrestrial laser scanner, Antonio Galgaro and, Giordano Teza, Nereo Preto, Marco Franceschi, Stefano Girardi, Arianna Pesci, 64(6):522–528, , 2009

78. Surface moisture and vegetation influences on lidar intensity data in an agricultural watershed, Kevin Garroway, Rob Jamieson, Christopher Hopkinson and, 37(3):275–284, , 2011

79. 3d reconstruction of building facade with fused data of terrestrial lidar data and optical image, Yehua Sheng and, Lin Yang, Bo Wang, 127(4):2165–2168, , 2016

80. Intensity correction of terrestrial laser scanning data by estimating laser transmission function, Fan Zhang and, Deren Li, Xianfeng Huang, Wei Fang, IEEE Transactions on Geoscience and Remote Sensing, 53(2):942–951, , 2014

81. The 3d hough transform for plane detection in point clouds: A review and a new accumulator design, Dorit Borrmann, Andreas N¨uchter, Kai Lingemann and, Jan Elseberg, 3D Research, 2(2):1–13, , 2011

82. Correction of incidence angle and distance effects on tls intensity data based on reference targets, Xiaojun Cheng, Kai Tan and, Remote Sensing, 8(3):251, , 2016

83. Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning, Long Chen, Jian Yang and, Tian Xia, Automation in Construction, 133:103992, , 2022

84. Specular reflection effects elimination in terrestrial laser scanning intensity data using phong model, Kai Tan and, Xiaojun Cheng, Remote Sensing, 9(8):853, , 2017

85. Applications of 3d point cloud data in the construction industry: A fifteenyear review from 2004 to 2018, MinKoo Kim, Qian Wang and, Advanced Engineering Informatics, 39:306–319, , 2019

86. Focusing attention on biological markers of acute stressor intensity: Empirical evidence and limitations, Antonio Armario, Roser Nadal, Javier Labad and, 111:95–103, , 2020

87. Marked watershed algorithm combined with morphological preprocessing based segmentation of adherent spores, Hui Li, Wei Chen, Yu Wang, Yaochi Zhao, Jiaying Wang, Zhuhua Hu, Yugui Han and, In Communications, Signal Processing, and Systems: Proceedings of the 8th International Conference on Communications, Signal Processing, and Systems 8th, pages 1316–1323. Springer, , 2020

88. Detailed threedimensional building fa¸cade reconstruction: a review on applications, data and technologies, Richard Leach and, Stephen Grebby, Stefano Cavazzi, Anna Klimkowska, 14(11):2579, , 2022

89. Urban vegetation detection using radiometrically calibrated smallfootprint fullwaveform airborne lidar data, Bernhard H¨ofle, Markus Hollaus and, Julian Hagenauer, 67:134–147, , 2012

90. SEMANTIC SEGMENTATION FOR BUILDING FA¸cADE 3d POINT CLOUD FROM 2d ORTHOPHOTO IMAGES USING TRANSFER LEARNING, E. Alby, C. Lhenry, T. Landes, P. Grussenmeyer and, A. Murtiyoso, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIIIB22021:201–206, jun 2021., , 2021

91. Segmentation of structural elements from 3d point cloud using spatial dependencies for sustainability studies, Tomo Inoue, Joram Ntiyakunze and, 23(4):1924,, , 2023

92. A review of lidar radiometric processing: From ad hoc intensity correction to rigorous radiometric calibration, Christopher E Parrish and, Alireza G Kashani, Michael J Olsen, Nicholas Wilson, 15(11):28099–28128, , 2015

93. Application of terrestrial laser scanning (tls) in the architecture, engineering and construction (aec) industry, Chao Wu, Yang Tang and, Boquan Tian, Yongbo Yuan, 22(1):265, , 2021

94. Segmentation of building point cloud models including detailed architectural/structural features and mep systems, Andrey Dimitrov and, Mani GolparvarFard, Automation in Construction, 51:32–45, , 2015

95. Geometric calibration and radiometric correction of lidar data and their impact on the quality of derived products, Ana P Kersting, WaiYeung Yan, Ayman F Habib, Ahmed Shaker and, 11(9):9069–9097, , 2011

96. HIGH QUALITY FACADE SEGMENTATION BASED ON STRUCTURED RANDOM FOREST, REGION PROPOSAL NETWORK AND RECTANGULAR FITTING, K. Rahmani and, H. Mayer, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV2:223–230, , 2018

97. Improved building facade segmentation through digital twinenabled randlanet with empirical intensity correction model, Yusen Wang, Michael Bekele Maru, Seunghee Park, Hyungchul Yoon and, Hansun Kim, 78:107520, 2023, , 2023

98. Analysis of incidence angle and distance effects on terrestrial laser scanner intensity: Search for correction methods, Antero Kukko, Anssi Krooks and, Mikko Kaasalainen, Sanna Kaasalainen, Anttoni Jaakkola, Remote sensing, 3(10):2207–2221, , 2011

99. Improving classification accuracy of airborne lidar intensity data by geometric calibration and radiometric correction, Ahmed Shaker, Ana Paula Kersting, Wai Yeung Yan, Ayman Habib and, 67:35–44, , 2012

100. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure, Burcu Akinci and, Kristina Georgieva, Paul Fieguth, Christian Koch, Varun Kasireddy, Advanced Engineering Informatics, 29(2):196–210, , 2015

101. Topolap: topology recovery for building reconstruction by deducing the relationships between linear and planar primitives, Qian Li, Xinyi Liu, Yongjun Zhang, Yi Wan, Xiao Ling, Linyu Liu and, 11(11):1372, , 2019

102. Terrestrial laser scanner intensity correction for the incidence angle effect on surfaces with different colours and sheens, D Bolkas, 40(18):7169–7189, , 2019

103. Automated asbuilt 3d reconstruction of civil infrastructure using computer vision: Achievements, opportunities, and challenges, Habib Fathi, Manolis Lourakis, Fei Dai and, Advanced Engineering Informatics, 29(2):149–161, , 2015

104. Automatic reconstruction of asbuilt building information models from laserscanned point clouds: A review of related techniques, Alan Lytle, Daniel Huber, Robert Lipman and, Burcu Akinci, Pingbo Tang, Automation in construction, 19(7):829– 843, , 2010

105. Correction of terrestrial lidar intensity channel using oren–nayar reflectance model: An application to lithological differentiation, MarcHenri Derron and, Battista Matasci, Michel Jaboyedoff, Florian Humair, Dario Carrea, Antonio Abellan, 113:17–29, , 2016

106. Automatic identification of street trees with improved randlanet and accurate calculation of shading area with densitybased iterative αshape, Shan Zhao, Juan Lei, YongjiWang, Ge Zhu, Yirui Jiang and, Hongwei Li, 10:132384–132395,, , 2022