The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B5-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B5-2020, 207–211, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B5-2020-207-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B5-2020, 207–211, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B5-2020-207-2020

  24 Aug 2020

24 Aug 2020

THE ISPRS BENCHMARK ON INDOOR MODELLING – PRELIMINARY RESULTS

K. Khoshelham1, H. Tran1, D. Acharya1, L. Díaz Vilariño2, Z. Kang3, and S. Dalyot4 K. Khoshelham et al.
  • 1Dept. of Infrastructure Engineering, The University of Melbourne, Parkville 3010 Australia
  • 2Applied Geotechnologies Group, School of Industrial Engineering, University of Vigo, Spain
  • 3Dept. of Remote Sensing and Geo-Information Engineering, School of Land Science and Technology, China University of Geosciences, Beijing 100083, China
  • 4Environmental Crowdsourcing Laboratory, Faculty of Civil and Environmental Engineering, Technion - Israel Institute of Technology, Haifa 3200003, Israel

Keywords: 3D modelling, Reconstruction, Point cloud, BIM, Quality, Evaluation, Performance, Benchmarking, Automation

Abstract. Automated 3D reconstruction of indoor environments from point clouds has been a topic of intensive research in recent years. Different methods developed for the generation of 3D indoor models have achieved promising results on different case studies. However, a comprehensive evaluation and comparison of the performance of these methods has not been available. This paper presents the preliminary results of the ISPRS benchmark on indoor modelling, an initiative of Working Group IV/5 to benchmark the performance of indoor modelling methods using a public dataset and a comprehensive evaluation framework. The performances of the different methods are compared through geometric quality evaluation of the reconstructed models in terms of completeness, correctness, and accuracy of wall elements. The results show that the reconstruction methods generally achieve high completeness but lower correctness for the reconstructed models while accuracies range from 0.5 cm to 6.7 cm.