19 Sep 2018
19 Sep 2018
AN EVALUATION FRAMEWORK FOR BENCHMARKING INDOOR MODELLING METHODS
K. Khoshelham1, H. Tran1, L. Díaz-Vilariño2, M. Peter3, Z. Kang4, and D. Acharya1
K. Khoshelham et al.
K. Khoshelham1, H. Tran1, L. Díaz-Vilariño2, M. Peter3, Z. Kang4, and D. Acharya1
- 1Dept. of Infrastructure Engineering, University of Melbourne, Parkville 3010 Australia
- 2Applied Geotechnologies Group, Dept. of Natural Resources and Environmental Engineering, University of Vigo, Spain
- 3Dept. of Earth Observation Science, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, The Netherlands
- 4Dept. of Remote Sensing and Geo-Information Engineering, School of Land Science and Technology, China University of Geosciences, Beijing 100083, China
- 1Dept. of Infrastructure Engineering, University of Melbourne, Parkville 3010 Australia
- 2Applied Geotechnologies Group, Dept. of Natural Resources and Environmental Engineering, University of Vigo, Spain
- 3Dept. of Earth Observation Science, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, The Netherlands
- 4Dept. of Remote Sensing and Geo-Information Engineering, School of Land Science and Technology, China University of Geosciences, Beijing 100083, China
Hide author details
Keywords: 3D reconstruction, Automation, Point cloud, BIM, Quality, Evaluation, Performance, Indoor navigation
Despite recent progress in the development of methods for automated reconstruction of indoor models, a comparative performance evaluation of these methods is not available due to the lack of publicly available benchmark datasets and a common evaluation framework. The ISPRS Benchmark on Indoor Modelling is an effort to enable comparison and benchmarking of indoor modelling methods by providing a benchmark dataset and a comprehensive evaluation framework. In this paper, we propose a framework for the evaluation of indoor modelling methods, and discuss various quality aspects of the reconstruction methods as well as the reconstructed models. We discuss the challenges in quantitative quality evaluation of indoor models through comparison with a reference model, and propose suitable measures and methods for comparing an automatically reconstructed indoor model with a reference.