An Automatic and Threshold-Free Performance Evaluation System for Building Extraction Techniques From Airborne LIDAR Data
- 14 May 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 7 (10), 4184-4198
- https://doi.org/10.1109/jstars.2014.2318694
Abstract
Some performance evaluation systems for building extraction techniques are manual in the sense that only visual results are provided or human judgment is employed. Many evaluation systems that employ one or more thresholds to ascertain whether an extracted building or roof plane is correct are subjective and cannot be applied in general. There are only a small number of automatic and threshold-free evaluation systems, but these do not necessarily consider all special cases, e.g., when over- and under-segmentation occurs during the extraction of roof planes. This paper proposes an automatic and threshold-free evaluation system that offers robust object-based evaluation of building extraction techniques. It makes one-to-one correspondences between extracted and reference entities using the maximum overlaps. Its application to the evaluation of a building extraction technique shows that it estimates different performance indicators including segmentation errors. Consequently, it can be employed for bias-free evaluation of other techniques whose outputs consist of polygonal entities.Keywords
Funding Information
- Australian Research Council (DE120101778)
This publication has 45 references indexed in Scilit:
- A graph edit dictionary for correcting errors in roof topology graphs reconstructed from point cloudsISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Land cover classification using airborne LiDAR products in Beauport, Québec, CanadaInternational Journal of Image and Data Fusion, 2013
- Filtering airborne LiDAR data by embedding smoothness-constrained segmentation in progressive TIN densificationISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Automatic extraction of building roofs using LIDAR data and multispectral imageryISPRS Journal of Photogrammetry and Remote Sensing, 2013
- A Multi-Resolution Hybrid Approach for Building Model Reconstruction from Lidar DataThe Photogrammetric Record, 2012
- A Hybrid Approach for Building Extraction From Spaceborne Multi-Angular Optical ImageryIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Area-wide roof plane segmentation in airborne LiDAR point cloudsComputers, Environment and Urban Systems, 2011
- Quality assessment of 3D building dataThe Photogrammetric Record, 2010
- Extraction of building footprints from airborne laser scanning: Comparison and validation techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Contributions to a quality description of areal objects in spatial data setsISPRS Journal of Photogrammetry and Remote Sensing, 2000