A Method for Post-hazard Assessment Through Topography Analysis using Regional Segmentation for Multi-temporal Satellite Imagery: A Case Study of 2011 Tohuku Earthquake Region

Pushan Kumar Dutta, O.P. Mishra, M.K. Naskar
2013 International Journal of Image Graphics and Signal Processing  
Non-rigid image registration in ext racting deformation map for two satellite images of the same region before and after earthquake occurrence based on measure of intensity dissimilarity C(Ir, T(If)) can play a significant ro le in post hazard analysis. In this paper, we have proposed a novel image transformation and regional segmentation of the same visualized region by assigning displacement label to change in intensity using Advanced Synthetic Aperture Radar (ASAR) satellite images. We used
more » ... te images. We used graph cut based non rig id reg istraion with a data term and a s moothness term for assigning markovianity between neighboring pixels. Displacement labels has been directly assigned fro m this data term for small intensity difference. Secondly, our data term imposes stricter penalty for intensity mis matches and hence yields higher registration accuracy. Based on the satellite image analysis through image segmentation, it is found that the area of .997 km 2 for the Honshu region was a maximu m damage zone localized in the coastal belt of NE Japan fore-arc region. A further objective has been to correlate fractal analysis of seismic clustering behavior with image segmentation suggesting that increase in the fractal dimension coefficient is associated with the deviation of the pixel values that gives a met ric of the devastation of the de-clustered region. image segmentation has also been used like demons [12] , turbo pixel decomposition [13], graph cuts [14] and CSC segmentation [15] . A graph cut image registration technique has been proposed for extraction of damage reg ion along the entropy and fractal distribution models for damage information along the coastline of Tohoku. In fact, image segmentation using graph cut can be understood as the process of assigning a label to every pixel in an image, the same Segmentation for Multi-temporal Satellite Imagery : A Case Study of 2011 Tohuku Earthquake Region
doi:10.5815/ijigsp.2013.10.08 fatcat:jw7zhrzrbbgljh4x3epes5avn4