Online CS-based SAR Edge-Mapping

2026-04-21

AI Summary

This work addresses the challenge of achieving real-time automatic target recognition (ATR) on resource-constrained small unmanned aerial vehicle (UAV)-borne synthetic aperture radar (SAR) systems. The authors propose an online compressive sensing edge mapping method that bypasses conventional image reconstruction entirely, directly generating sparse edge maps from raw echo signals for scene and target classification. By integrating compressive sensing, an online processing architecture, and edge mapping techniques, the approach substantially reduces both the number of required samples and computational overhead. Compared to classical SAR reconstruction methods, the proposed scheme significantly lowers data volume and computational demands, thereby enabling efficient real-time ATR on platforms with limited resources.

Technology Category

Machine Learning: Learning on the Edge & Model CompressionComputer Vision: Remote Sensing / Geospatial AIPlanning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

With modern defense applications increasingly relying on inexpensive, small Unmanned Aerial Vehicles (UAVs), a major challenge lies in designing intelligent and computationally efficient onboard Automatic Target Recognition (ATR) algorithms to carry out operational objectives. This is especially critical in Synthetic Aperture Radar (SAR), where processing techniques such as ATR are often carried out post data collection, requiring onboard systems to bear the memory burden of storing the back-scattered signals. To alleviate this high cost, we propose an online, direct, edge-mapping technique which bypasses the image reconstruction step to classify scenes and targets. Furthermore, by reconstructing the scene as an edge-map we inherently promote sparsity, requiring fewer measurements and computational power than classic SAR reconstruction algorithms such as backprojection.

Problem

• Synthetic Aperture Radar
• Automatic Target Recognition
• Unmanned Aerial Vehicles
• Edge Mapping
• Computational Efficiency

Innovation

• Compressive Sensing
• Synthetic Aperture Radar
• Edge Mapping
• Automatic Target Recognition
• Online Processing