[2508.00307] Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2508.00307 (eess) [Submitted on 1 Aug 2025 (v1), last revised 26 Mar 2026 (this version, v2)] Title:Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD Authors:Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwant Bethy, Saeed Afshar View a PDF of the paper titled Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD, by Belman Jahir Rodriguez and 4 other authors View PDF HTML (experimental) Abstract:We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, ...