GeoComp benchmarks

SZTAKI AirChange Benchmark set

A Ground truth collection for change detection in optical aerial images taken with several years time differences

co-authors: Csaba Benedek and Tamás Szirányi (MTA SZTAKI)

Description

This Benchmark set contains 13 aerial image pairs of size 952x640 and resolution 1.5m/pixel and binary change masks (drawn by hand), which were used for evaluation in publications [1] and [2].

Each record constains a pair of preliminary registered input images and a mask of the 'relevant' changes. The input images are taken with 5, 7 resp. 23 years time differences. During the generation of the change mask, we have considered the following differences as relevant changes: (a) new built-up regions (b) building operations (c) planting of large group of trees (d) fresh plough-land (e) groundwork before building over. Note that the ground truth does NOT contain change classification, only binary change-no change decision for each pixel. For more information please contact Csaba Benedek.

Sample images:

Test set	Image 1	Image 2	GT change mask
SZADA
TISZADOB
ARCHIVE

 

Terms of usage:

The benchmark set is free for scientific use.

- Please acknowledge the use of the benchmark by referring to our relevant publications [1] and [2].
- Please notify us if a publication using the benchmark set appears.

Download:

DOWNLOAD BENCHMARK (~42MB)

For password, please contact Csaba Benedek in e-mail: benedek.csaba_at_sztaki.mta.hu

References

[1] Cs. Benedek and T. Szirányi: ”Change Detection in Optical Aerial Images by a Multi-Layer Conditional Mixed Markov Model”, IEEE Transactions on Geoscience and Remote Sensing, vol. 47, no. 10, pp. 3416-3430, 2009

[2] Cs. Benedek and T. Szirányi: ”A Mixed Markov Model for Change Detection in Aerial Photos with Large Time Differences”, International Conference on Pattern Recognition (ICPR), Tampa, Florida, USA, December 8-11, 2008

[3] Cs. Benedek: "Change Detection in Optical Aerial Images by a Multi-Layer Conditional Mixed Markov Model", invited seminar at the Florida State University, Department of Statistics, Tallahassee, Florida, USA, 16 December 2008