Image Change Detection for Earthquake Damage Assessment

Sanjay Kumar Jain, Ashok Kumar Dubey


The work presented here is concerned with the problem of Earthquake damage assessment using multi temporal satellite images. Remotely sensed data can provide valuable information for disaster assessment such as Earthquakes, Volcanic Eruptions, Landslides, Floods, Storm Surge, Hurricanes, Fires and Drought etc. Earthquake is one of the unavoidable natural hazards that cause lots of damages and problems to the economy, environment and the whole life of people. Prevention of earthquake is rarely achieved and such events continue to pose increasing threat to life and property. After the earthquakes, there is a need for rapid, accurate and reliable damage information in the critical post event hours to guide response activities. In this work, we focused on image change detection based Earthquake damage assessment. For experimental purpose, we have collected the pre and post panchromatic and multi-spectral images of Haiti earthquake which was occurred in 12 Jan 2010. Various image change detection methods are suggested in the literature such as simple differencing, statistical change detection, likelihood ratio test, PCA etc. We have proposed a Minimum Description Length (MDL) based method for image change detection. The results generated by the proposed method are quite promising in comparison to other change detection methods and are helpful for precise earthquake damage assessment.



Keywords: Change detection, Damage assessment, Minimum Description length, Remote sensing

Full Text:




  • There are currently no refbacks.

Copyright (c) 2016 International Journal of Advanced Research in Computer Science