SAVERS: SAR ATR with Verification Support Based on Convolutional Neural Network
This work addresses SAR ATR for military or surveillance applications, but it is incremental as it builds on prior CNN methods by adding verification support.
The authors tackled the problem of synthetic aperture radar automatic target recognition by proposing SAVERS, a CNN that performs coarse and fine segmentation to classify targets from arbitrary-sized imagery, achieving evaluation results on the MSTAR dataset.
We propose a new convolutional neural network (CNN) which performs coarse and fine segmentation for end-to-end synthetic aperture radar (SAR) automatic target recognition (ATR) system. In recent years, many CNNs for SAR ATR using deep learning have been proposed, but most of them classify target classes from fixed size target chips extracted from SAR imagery. On the other hand, we proposed the CNN which outputs the score of the multiple target classes and a background class for each pixel from the SAR imagery of arbitrary size and multiple targets as fine segmentation. However, it was necessary for humans to judge the CNN segmentation result. In this report, we propose a CNN called SAR ATR with verification support (SAVERS), which performs region-wise (i.e. coarse) segmentation and pixel-wise segmentation. SAVERS discriminates between target and non-target, and classifies multiple target classes and non-target class by coarse segmentation. This report describes the evaluation results of SAVERS using the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset.