Radar vision

The authors discusses a novel idea, for which he has coined the term radar vision (Haykin 1990). The goal is to make radar an intelligent remote sensing device, such that it is capable of developing cognition of the surrounding environment. To illustrate the main points of this new idea, he uses the case of a coherent marine radar for ocean surveillance. The special targets of interest include growlers (pieces of ice with small visible radar cross-sections) and fishing boats. These targets are too weak for detection by conventional marine radar techniques. In a radar vision system the combination of a receptive field, a memory, and a neural network classifier provides a learning capability. The knowledge processor makes it possible to incorporate prior information, and concurrent information obtained from auxiliary sensors (e.g. weather instruments) and human inputs (visual confirmation). Finally, the feedback from the receiver to the transmitter enables the system to adaptively match the transmitted illumination to the characteristics of the environment.<
>