A hyperspectral data set can be used for testing binary and multi-class change detection techniques.
All the files are in .mat format that can be loaded in Matlab.
PreImg_2006: Pre-processed Hyperion image acquired on May 3, 2005;
PostImg_2007: Pre-processed Hyperion image acquired on April 23, 2007;
Reference_Map_Binary: A binary reference map for evaluting the binary change detection performance (Two classes: change and no-change).
Reference_Map_Multiclass: A multiclass reference map for evaluting the multiclass change detection performance (Six classes: five change classes and no-change).
This dataset is made up of a pair of bitemporal hyperspectral images acquired by the Hyperion sensor mounted on board the EO-1 satellite on May 3, 2006 and April 23, 2007. The study area is wetland agricultural land in Yancheng, Jiangsu Province, China, which has a size of 220 × 430 pixels.
Preprocessing operations were made (i.e., repairing bad stripes, removal of uncalibrated and noisiest bands, atmospheric correction, co-registration) on two images, where 128 bands (i.e., bands 13–53, 85–96, 103–118, 135–164, 188–199, and 202–218) out of original 242 bands were selected.
In this scenario, five major land-cover change classes are present, mainly associated with the changes between vegetation, bare land, water, and soil.
(a) May 3, 2006; (b) April 23, 2007; (c) Binary CD Reference Map; (d) Multiclass CD Reference Map
Change Class 1 (C1): 8937 pixels
Change Class 2 (C2): 14520 pixels
Change Class 3 (C3): 115 pixels
Change Class 4 (C4): 423 pixels
Change Class 5 (C5): 163 pixels
No-change Class (NC): 70442 pixels
Total: 94600 pixels
If you use this data set for your research, please cite the following papers.
[1] S. Liu, D. Marinelli, L. Bruzzone and F. Bovolo, "A Review of Change Detection in Multitemporal Hyperspectral Images: Current Techniques, Applications, and Challenges," IEEE Geoscience and Remote Sensing Magazine, vol. 7, no. 2, pp:140-158, 2019. DOI: 10.1109/MGRS.2019.2898520
[2] S. Liu, Q. Du, X. Tong, A. Samat, H. Pan , X. Ma, “Band Selection based Dimensionality Reduction for Change Detection in Multitemporal Hyperspectral Images,” Remote Sensing, vol. 9, no.10, pp:1008, 2017. DOI: 10.3390/rs9101008
[3] S. Liu, Q. Du, X. Tong, A. Samat, L. Bruzzone, “Unsupervised Change Detection in Multispectral Remote Sensing Images via Spectral-Spatial Band Expansion,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 9, pp:3578-3587, 2019. DOI: 10.1109/JSTARS.2019.2929514