Building Detection Benchmark is OPEN!!!


The automated detection of urban objects from data acquired by satellite sensors has been an important topic of research in remote sensing & pattern recognition.

The aim of this benchmark is to provide image patches tested in [1], which can be used by interested researchers in order to test their own methods on building detection task.

An information about the image data set provided through the benchmark is here.

We also provide interested researchers an Online Performance Evaluation script (thanks to Dr. Caglar Senaras) to test their results with the evaluation strategy presented in [2] and [3].

The benchmark data set is here.

The ground truth data set is here.

The results of state-of-the-art approaches are here.


[1] Manno-Kovács, A., Ok, A. O., 2015, Building Detection from Monocular VHR Images by Integrated Built-in Area Knowledge, IEEE Geoscience and Remote Sensing Letters, vol. 12, no. 10, pp. 2140-2144. (download)

[2] Ok, A. O., Senaras, C., Yuksel, B., 2013, Automated Detection of Arbitrarily-Shaped Buildings in Complex Environments from Monocular VHR Optical Satellite Imagery, IEEE Transactions on Geoscience and Remote Sensing, vol. 51, no. 3, pp. 1701-1717. (download)

[3] Ok, A. O., 2013, Automated Detection of Buildings from Single VHR Multispectral Images using Shadow Information and Graph Cuts, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 86, (2013), pp. 21-40. (download)

Latest Announcements