Details
| Original language | English |
|---|---|
| Pages (from-to) | 11-20 |
| Number of pages | 10 |
| Journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Volume | 2 |
| Issue number | 1 |
| Publication status | Published - 1 Mar 2009 |
Abstract
In this paper, different methods for the evaluation of building detection algorithms are compared. Whereas pixel-based evaluation gives estimates of the area that is correctly classified, the results are distorted by errors at the building outlines. These distortions are potentially in an order of 30%. Object-based evaluation techniques are less affected by such errors. However, the performance metrics thus delivered are sometimes considered to be less objective, because the definition of a “correct detection” is not unique. Based on a critical review of existing performance metrics, selected methods for the evaluation of building detection results are presented. These methods are used to evaluate the results of two different building detection algorithms in two test sites. A comparison of the evaluation techniques shows that they highlight different properties of the building detection results. As a consequence, a comprehensive evaluation strategy involving quality metrics derived by different methods is proposed.
Keywords
- Airborne laser scanning (ALS), automatic building extraction, metrics, object detection, object-based error assessment, performance evaluation
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Earth and Planetary Sciences(all)
- Atmospheric Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 2, No. 1, 01.03.2009, p. 11-20.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A Comparison of Evaluation Techniques for Building Extraction from Airborne Laser Scanning
AU - Rutzinger, Martin
AU - Rottensteiner, Franz
AU - Pfeifer, Norbert
N1 - Funding Information: Manuscript received October 30, 2007; revised August 28, 2008. First published March 04, 2009; current version published April 29, 2009. This work supported in part by the research program of the CRC for Spatial Information, established and supported under the Australian Cooperative Research Centres Program.
PY - 2009/3/1
Y1 - 2009/3/1
N2 - In this paper, different methods for the evaluation of building detection algorithms are compared. Whereas pixel-based evaluation gives estimates of the area that is correctly classified, the results are distorted by errors at the building outlines. These distortions are potentially in an order of 30%. Object-based evaluation techniques are less affected by such errors. However, the performance metrics thus delivered are sometimes considered to be less objective, because the definition of a “correct detection” is not unique. Based on a critical review of existing performance metrics, selected methods for the evaluation of building detection results are presented. These methods are used to evaluate the results of two different building detection algorithms in two test sites. A comparison of the evaluation techniques shows that they highlight different properties of the building detection results. As a consequence, a comprehensive evaluation strategy involving quality metrics derived by different methods is proposed.
AB - In this paper, different methods for the evaluation of building detection algorithms are compared. Whereas pixel-based evaluation gives estimates of the area that is correctly classified, the results are distorted by errors at the building outlines. These distortions are potentially in an order of 30%. Object-based evaluation techniques are less affected by such errors. However, the performance metrics thus delivered are sometimes considered to be less objective, because the definition of a “correct detection” is not unique. Based on a critical review of existing performance metrics, selected methods for the evaluation of building detection results are presented. These methods are used to evaluate the results of two different building detection algorithms in two test sites. A comparison of the evaluation techniques shows that they highlight different properties of the building detection results. As a consequence, a comprehensive evaluation strategy involving quality metrics derived by different methods is proposed.
KW - Airborne laser scanning (ALS)
KW - automatic building extraction
KW - metrics
KW - object detection
KW - object-based error assessment
KW - performance evaluation
UR - http://www.scopus.com/inward/record.url?scp=66149101328&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2009.2012488
DO - 10.1109/JSTARS.2009.2012488
M3 - Article
AN - SCOPUS:66149101328
VL - 2
SP - 11
EP - 20
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
SN - 1939-1404
IS - 1
ER -