EARTHQUAKE DESTRUCTION ASSESSMENT OF URBAN ROADS NETWORK USING SATELLITE IMAGERY AND FUZZY INFERENCE SYSTEMS

The idea of assessing the damages to roads network after earthquake strikes has been referred as a matter of importance for performing every systematically planned activity in the affected region. When gathering information about the devastated region is crucially costly and time-consuming and in most cases impossible, high-resolution satellite imagery is hired to provide fast and accurate information for every assessment and evaluation processes. Therefore, this research is mainly focused on design and development of a method to evaluate the damages to the roads network, using pre-event digital vector map and post-event highresolution satellite imagery. In this case, using pre-event digital vector map and post-event satellite imagery, the roads network is extracted and then processed for determination of road blocks across city roads network. The existence of many violating objects at the scene of satellite imagery may mislead the process of finding blocked roads. Therefore, violating objects are detected and removed through Fuzzy engines. Then, analyzing the spectral and textural properties and comparing specific computed set of descriptors, the damage and no-damage objects are marked. Through inspecting the results, hiring Fuzzy Inference Systems, the blocked road sections in the region are detected. The proposed method is evaluated using digital vector map and QuickBird Pansharpened images of the city of Bam, located southwest of Iran regarding to the devastating earthquake in December 2003. The visual inspections have confirmed the capabilities of the method for evaluation urban road network after earthquake strikes.

[1]  S. K. Parui,et al.  An improved backpropagation neural network for detection of road-like features in satellite imagery , 1997 .

[2]  T. Ranchin,et al.  Mapping of Urban Areas: A Multiresolution Modeling Approach for Semi-Automatic Extraction of Streets , 2000 .

[3]  Xiangyun Hu,et al.  Automatic Road Extraction from Dense Urban Area by Integrated Processing of High Resolution Imagery and Lidar Data , 2004 .

[4]  Mehdi Mokhtarzade,et al.  Road detection from high-resolution satellite images using artificial neural networks , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Ruzena Bajcsy,et al.  Computer Recognition of Roads from Satellite Pictures , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Haihong Li,et al.  Road extraction from aerial and satellite images by dynamic programming , 1995 .

[7]  Charles K. Huyck,et al.  Damage Assessment with Very-High Resolution Optical Imagery Following the December 26, 2003 Bam, Iran Earthquake , 2005 .

[8]  Babak Mansouri,et al.  Methodologies for Post-Earthquake Building Damage Detection Using SAR and Optical Remote Sensing , 2004 .

[9]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[10]  A. Gruen,et al.  Semi-Automatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes , 1997 .

[11]  L. Chiroiu,et al.  DAMAGE ASSESSMENT USING HIGH RESOLUTION SATELLITE IMAGERY: APPLICATION TO 2001 BHUJ, INDIA, EARTHQUAKE , 2001 .

[12]  C. Steger,et al.  AUTOMATIC ROAD EXTRACTION BASED ON MULTI-SCALE, GROUPING, AND CONTEXT , 1999 .

[13]  Dan Klang,et al.  AUTOMATIC DETECTION OF CHANGES IN ROAD DATABASES USING SATELLITE IMAGERY , 2003 .

[14]  P. Ram,et al.  Engineering and Organizational Issues Before,During and After Hurricane Katrina , 2007 .