Infrared region classification using texture and model-based features

Infrared sensors are widely utilized on manned and unmanned systems due to their ability to operate during low light conditions as well as their target discrimination capability. Machine vision algorithms that operate on infrared imagery (e.g. target detection, obstacle detection, target tracking) can significantly increase the effectiveness of platforms and the autonomy of unmanned systems. The classification of regions in infrared imagery provides a valuable input to computer vision algorithms. This paper contains an analysis of features for infrared region discrimination, feature dimensionality reduction, and classification for regions of infrared imagery. A variety of features are considered including those based on texture and a physics based model for atmospheric attenuation. An analysis of the optimal feature set and classifier combination is presented. Performance of the classifier on a database of infrared imagery is provided as well as top level contextual techniques to improve classification performance.

1. INTRODUCTION

Infrared sensors are employed for a large variety of commercial and military applications. The imagery produced by these sensors provides significant information to human operators and are widely used for machine vision algorithms such as target detection. Infrared sensors are also frequently installed on unmanned systems including unmanned air vehicles (UAVs), unmanned ground vehicles (UGVs), and unattended remote sensors. In order to improve the autonomy of these systems, it is essential that the autonomous system awareness from the imagery collected by these systems be increased. A passive technique for obtaining situational awareness is the analysis of imagery for scene understanding. The first step in scene understanding is to classify imagery regions.