Simultaneous Registration, Segmentation and Change Detection from Multisensor, Multitemporal Satellite Image Pairs

Vakalopoulou M., Platias C., Papadomanolaki M., Paragios N*., Karantzalos K.

NTUA, Greece

 * ECP, France
Corresponding authors: mariavak@central.ntua.gr & karank@central.ntua.gr

A novel generic graph-based framework was developed addressing simultaneous registration, segmentation and change detection in multisensor data of different spectral, spatial and temporal resolutions. The quite promising experimental results indicated: (i) for the registration task a mean displacement error of less than 2 pixels, (ii) for the segmentation task in most cases completeness and correctness rates above 77% and (iii) for the change detection around or above 70%. The main errors derived from the important relief displacements around the tallest buildings and from the quite similar reflectance spectra of the different man-made objects including ship/vessels.

 

Registration Results

While considering as reference an image or map, the developed framework can register various multi-sensor datasets and simultaneously perfom image segmentation and change detection

 

 

Multi-modal Data Registration

D1: Deimos-2 May'15, D2: Deimos-2 March'15, V: One frame from the Iris Video sequence, G: Google Image Mosaic

 

 

Deimos-2 (March'15) registration to Google's mosaic

 

Deimos-2 (May'15) registration to Google's mosaic