Deep Learning Approach for SAR Image Retrieval for Reliable Positioning in GPS-Challenged Environments

This article presents a comprehensive approach to synthetic aperture radar (SAR) image retrieval for navigation in global positioning system (GPS)-denied areas. It explores the utilization of SAR images to develop navigation techniques, assuming the system can generate real-time SAR images. The navigation process involves image retrieval, where a query image is compared to stored images in a database to identify the most similar ones. The selected images serve as reference points for extracting precise location coordinates. We propose model leveraging on the notion of Siamese artificial neural networks (ANNs), inspired by the SqueezeNet architecture, that incorporates swish activation functions and a retrieval module to address challenges related to variations in unmanned aerial vehicle (UAV) height and rotations. Extensive evaluation demonstrates the effectiveness of the proposed method, with low retrieval error and feasibility for computationally constrained devices. The stability of the method is also validated using out-of-sample data. Overall, this work contributes to the advancement of SAR image retrieval and navigation in GPS-denied environments, with potential applications in navigation, target detection, terrain classification, and more.