Target detection in fused X-band radar and IR images using the functional minimization approach to data association

摘要

Sensor data fusion is a process of combining information from multiple sources-sensors, databases, knowledge bases, and communication lines-in order to improve the performance of a system with respect to a system's goal. The goal of the system considered in this paper is target detection, and therefore, the performance measures relevant to this problem are the probability of detection and the probability of false alarms. The main issue addressed in this paper is whether target detection can be improved through fusing images collected from two sensors-an infrared (IR) camera and an X-band radar. In this work, we investigate the "fuse-then-abstract" approach. That is, we first fuse the radar image with the IR image, and then detect targets in the fused image.