Gravitational self-organizing map-based seismic image classification with an adaptive spectral-textural descriptor

Abstract

Seismic image classification is of vital importance for extracting damage information and evaluating disaster losses. With the increasing availability of high resolution remote sensing images, automatic image classification offers a unique opportunity to accommodate the rapid damage mapping requirements. However, the diversity of disaster types and the lack of uniform statistical characteristics in seismic images increase the complexity of automated image classification. This paper presents a novel automatic seismic image classification approach by integrating an adaptive spectral-textural descriptor into gravitational self-organizing map (gSOM). In this approach, seismic image is first segmented into several objects based on mean shift (MS) method. These objects are then characterized explicitly by spectral and textural feature quantization histograms. To objectify the image object delineation adapt to various disaster types, an adaptive spectral-textural descriptor is developed by integrating the histograms automatically. Subsequently, these objects as classification units are represented by neurons in a self-organizing map and clustered by adjacency gravitation. By moving the neurons around the gravitational space and merging them according to the gravitation, the object-based gSOM is able to find arbitrary shape and determine the class number automatically. Taking advantage of the diversity of gSOM results, consensus function is then conducted to discover the most suitable classification result. To confirm the validity of the presented approach, three aerial seismic images in Wenchuan covering several disaster types are utilized. The obtained quantitative and qualitative experimental results demonstrated the feasibility and accuracy of the proposed seismic image classification method.