Temperature-Driven Segmentation for Autonomous Anti-Tank Weapons

Abstract

In this paper we discuss a simple temperature-driven segmentation technique that can be used for autonomous terminal guidance of anti-tank munitions. A ratio between two images from different IR bands is taken to form an emissivity independent image that is a function of temperature only. Size and temperature discrimination can then be used to find hot spots of interest. Candidate targets are segmented from the image about the points of interest using an.algorithm that finds all regions in multi-region objects and does not require a priori intensity information. Size and gross shape features are used to determine if the segmented objects are to be classified as targets. The key to this approach is the initial hot spot extraction. The temperature dependent ratio image allows quick and confident screening of the entire field of view, so that only the regions of interest require further processing. The described techniques effectively found tanks in the presence of common battlefield clutter when used with synthetic IR imagery provided by Georgia Tech Research Institute. The simplicity, effectiveness and potential speed of this technique make it ideal for autonomous guidance of expendable anti-tank weapons, especially where only low resolution IR imagery is available.