Neural Edge Histogram Descriptors for Underwater Acoustic Target Recognition

2025/03/17 by Agashe, Atharva, Carreiro, Davelle, Van Dine, Alexandra +1
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2503.13763

Abstract

Numerous maritime applications rely on the ability to recognize acoustic targets using passive sonar. While there is a growing reliance on pre-trained models for classification tasks, these models often require extensive computational resources and may not perform optimally when transferred to new domains due to dataset variations. To address these challenges, this work adapts the neural edge histogram descriptors (NEHD) method originally developed for image classification, to classify passive sonar signals. We conduct a comprehensive evaluation of statistical and structural texture features, demonstrating that their combination achieves competitive performance with large pre-trained models. The proposed NEHD-based approach offers a lightweight and efficient solution for underwater target recognition, significantly reducing computational costs while maintaining accuracy.

Related

• Histogram Layer Time Delay Neural Networks for Passive Sonar Classification
• Quantitative Measures for Passive Sonar Texture Analysis
• DEMONet: Underwater Acoustic Target Recognition based on Multi-Expert Network and Cross-Temporal Variational Autoencoder
• Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
• Pre-trained Models for Sonar Images