ZoomSpec: A Physics-Guided Coarse-to-Fine Framework for Wideband Spectrum Sensing

2026-04-15

AI Summary

This work addresses the challenge of low-altitude wideband spectrum sensing, which is hindered by heterogeneous protocols, large bandwidths, and non-stationary signal-to-noise ratios. Existing data-driven approaches struggle to detect narrowband signals effectively due to their neglect of time–frequency resolution constraints and spectral leakage. To overcome these limitations, the authors propose ZoomSpec, a hybrid framework that integrates signal processing priors with deep learning through a two-stage coarse-to-fine architecture. ZoomSpec enhances narrowband structure clarity via Log-STFT, employs an adaptive heterodyne low-pass (AHLP) module for center-frequency alignment and bandwidth matching, and incorporates a dual-domain attention mechanism to fuse time-domain I/Q and spectral features. Evaluated on the real-world SpaceNet dataset, ZoomSpec achieves a state-of-the-art 78.1 mAP@0.5:0.95 and demonstrates robust performance across diverse modulation bandwidths.

Technology Category

• Machine Learning: Online Learning & Bandits
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Wideband spectrum sensing for low-altitude monitoring is critical yet challenging due to heterogeneous protocols,large bandwidths, and non-stationary SNR. Existing data-driven approaches treat spectrograms as natural images,suffering from domain mismatch: they neglect time-frequency resolution constraints and spectral leakage, leading topoor narrowband visibility. This paper proposes ZoomSpec, a physics-guided coarse-to-fine framework integrating signal processing priors with deep learning. We introduce a Log-Space STFT (LS-STFT) to overcome the geometric bottleneck of linear spectrograms, sharpening narrowband structures while maintaining constant relative resolution. A lightweight Coarse Proposal Net (CPN) rapidly screens the full band. To bridge coarse detection and fine recognition, we design an Adaptive Heterodyne Low-Pass (AHLP) module that executes center-frequency aligning, bandwidth-matched filtering, and safe decimation, purifying signals of out-of-band interference. A Fine Recognition Net (FRN) fuses purified time-domain I/Q with spectral magnitude via dual-domain attention to jointly refine temporal boundaries and modulation classification. Evaluations on the SpaceNet real-world dataset demonstrate state-of-the-art 78.1 mAP@0.5:0.95, surpassing existing leaderboard systems with superior stability across diverse modulation bandwidths.

Problem

• wideband spectrum sensing
• low-altitude monitoring
• spectral leakage
• time-frequency resolution
• narrowband visibility

Innovation

• Log-Space STFT
• Coarse-to-Fine Framework
• Adaptive Heterodyne Low-Pass
• Dual-Domain Attention
• Physics-Guided Spectrum Sensing