Deep Learning for End-to-End Automatic Target Recognition from Synthetic Aperture Radar Imagery
This work addresses the need for streamlined ATR in SAR imagery by replacing multi-stage pipelines with a single model, though it appears incremental as it builds on existing CNN approaches.
The authors tackled the problem of automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery by proposing an end-to-end convolutional neural network (VersNet) that integrates detection, discrimination, and classification stages, achieving results on the MSTAR dataset with outputs for 12 classes including target positions, classes, and poses.
The standard architecture of synthetic aperture radar (SAR) automatic target recognition (ATR) consists of three stages: detection, discrimination, and classification. In recent years, convolutional neural networks (CNNs) for SAR ATR have been proposed, but most of them classify target classes from a target chip extracted from SAR imagery, as a classification for the third stage of SAR ATR. In this report, we propose a novel CNN for end-to-end ATR from SAR imagery. The CNN named verification support network (VersNet) performs all three stages of SAR ATR end-to-end. VersNet inputs a SAR image of arbitrary sizes with multiple classes and multiple targets, and outputs a SAR ATR image representing the position, class, and pose of each detected target. This report describes the evaluation results of VersNet which trained to output scores of all 12 classes: 10 target classes, a target front class, and a background class, for each pixel using the moving and stationary target acquisition and recognition (MSTAR) public dataset.