Target broker compression for multi-level fusion

Information Fusion consists of low-level information fusion (LLIF) of object-level assessment which is subject to many operating conditions of the sensor type, environment conditions, and the targets. Likewise, high-level information fusion (HLIF) requires proactive management of sensor parameters. One example of a parameter that affects downstream information fusion tasks of target tracking and identification is that of upstream image compression. In this paper, we present a technique for analyzing the effects of image compression on the information fusion result. The compression selections are based on user needs, target type, and information fusion function, which is a subject of the operating conditions. Results are presented that modify the Video National Imagery Interpretability Ratio (VNIIRS) equations to include compression requirements for object recognition, fusion of results, and user selections. The target broker compression method would support image fusion system providing an exemplar of LLIF-HLIF interactions.