Color texture analysis applied to mine detection

In humanitarian demining activities is necessary to find complementary sensing methods. In this paper, a second stage of development of a complementary sensor for a metal detector is presented. This sensor is based on the analysis of images taken by an onboard camera. Images are processed by a color texture analysis. Based on the color texture analysis, this paper shows that it is possible to determine the presence of a non-metallic landmine within the image. This is achieved by finding the image regions whose color and texture features variations are considered anomalous. It is thought that the color and texture variations over the image are an indicator that the surface has been intentionally modified. This image processing strategy is being developed, in order to be implemented in robot 'Amaranta' (designed at Javeriana University, Colombia).