AIDED AND AUTOMATIC TARGET RECOGNITION BASED UPON SENSORY INPUTS FROMIMAGE FORMING SYSTEMS

This paper systematically reviews 10 years of research that several Ar my Laboratories conducted in object recognition algorithms, processors , and evaluation techniques. In the military, object recognition is ap plied to the discrimination of military targets, ranging from human-ai ded to autonomous operations, and is called Automatic Target Recogniti on (ATR). The research described here has been concentrated in human-a ided target recognition applications, but some attention has been paid to automatic processes. Definitions and performance metrics that have been developed are described along with performance data showing the present state-of-the-art. The effects of signal-to-noise and clutter p arameters are indicated in the data. Multisensor fusion and model-base d algorithms are discussed as the latest techniques under consideratio n by the military research community. The results demonstrate that use ful performance can be achieved, and tools are evolving to understand and improve the performance under real-world conditions. The reference d research strongly indicates the need for the development of image sc ience, as described in the paper, to support the theoretical underpinn ings of ATR.