No abstract

No abstract

Understanding the decision-making process of deep learning networks is a key challenge which has rarely been investigated for Synthetic Aperture Radar (SAR) images. In this paper, a set of new analytical tools is proposed and applied to a Convolutional Neural Network (CNN) handling Automatic Target Recognition (ATR) on two SAR datasets containing military targets. Firstly, an analysis of the respective influence of target, shadow and background areas on classification performance is carried out. The shadow appears to be the least used portion of the image affecting the decision process, compared to the target and clutter, respectively. Secondly, the location of the most influential features is determined with classification maps obtained by systematically hiding specific target parts and registering the associated classification rate (CR) relative to the images to be classified. The location of the image areas without which classification fails is target type and orientation specific. Nonetheless, a strong contribution of specific parts of the target, such as the target top and the areas facing the radar, is noticed. Lastly, results show that features are increasingly activated along the CNN depth according to the target type and its orientation, even though target orientation is absent from the loss function.

Radar systems require transmission of very high purity signals. Photonics is now mature enough to achieve analog transmission with very low noise, strong immunity, and wide-bandwidth even in harsh environments. We present our recent developments of optimized optical links dedicated to radar and multifunction systems.

No abstract