用于前视声呐图像中节能目标检测的脉冲神经网络

中文摘要 AI 辅助

自主水下航行器（AUV）是从科研、能源到国防等行业日益重要的工具。AUV是在偏远环境中运行的功率受限平台，电池容量固定，在漫长的任务期间，推进系统与计算、传感器争夺功率。AUV常运行在黑暗或浑浊水域，光学传感价值有限，依赖声呐作为主要传感方式。卷积神经网络（CNNs）是前视声呐（FLS）图像目标检测的最新解决方案，但能耗高（如YOLOv8m：每次推理322毫焦）。脉冲神经网络（SNNs）依赖二元脉冲激活，因此采用稀疏的仅累加操作，具有显著的节能性，尤其搭配专用神经形态硬件时。前视声呐回波的稀疏、高对比度结构与脉冲编码的匹配度，是光学图像所不具备的。此前尚无研究评估SNNs在FLS图像目标检测中的适用性。本研究将SpikeYOLO（一种采用代理梯度训练的全脉冲网络）在三个FLS目标检测数据集上与最新CNN基准进行了对比。关键结果：SpikeYOLO T=2在UATD数据集上实现了3.3倍的理论计算能耗降低（97毫焦对比322毫焦），且精度相当（mAP@0.5:0.529对比YOLOv8m的0.575）；在稀疏的Marine-Debris-FLS数据集上，SpikeYOLO的mAP@0.5与YOLOv8m相当，且比YOLO-SONAR和Fast R-CNN基准的能耗低4.4倍；SpikeYOLO对乘性斑点噪声的鲁棒性更优（σ=0.4时退化3.0%，而YOLOv8m为8.9%），在σ=0.6时直接优于YOLOv8m，与实际FLS部署直接相关。

英文摘要

Autonomous underwater vehicles (AUVs) are increasingly important tools in industries ranging from research, to energy, to defense. AUVs are power-constrained platforms operating in remote environments with fixed battery capacities, where propulsion competes with compute and sensors for power over lengthy mission durations. AUVs frequently operate in dark or turbid waters where optical sensing is of limited value, and rely on sonar as their primary sensing modality. Convolutional neural networks (CNNs) are the state-of-the-art solution for object detection in forward-looking sonar imagery, but are energy expensive (e.g. YOLOv8m: 322 mJ/inference). Spiking neural networks (SNNs) rely on binary spike activations and thus sparse accumulate-only operations, allowing them to be remarkably energy efficient, particularly when paired with dedicated neuromorphic hardware. The sparse, high-contrast structure of forward-looking sonar (FLS) returns is structurally matched to spike coding in a way that optical imagery is not. No prior work has assessed the suitability of SNNs for object detection in FLS imagery. SpikeYOLO, a fully spiking network trained with surrogate gradients, was benchmarked against state-of-the-art CNN baselines on three FLS object detection datasets. Key results: SpikeYOLO T=2 achieves 3.3$\times$ lower theoretical compute energy on UATD (97 vs 322 mJ) at competitive accuracy (0.529 mAP@0.5:0.95 vs. YOLOv8m's 0.575); SpikeYOLO matches YOLOv8m on mAP@0.5 and outperforms YOLO-SONAR and Fast R-CNN baselines on the sparse Marine-Debris-FLS dataset at 4.4$\times$ lower energy; SpikeYOLO demonstrates superior robustness to multiplicative speckle noise (3.0% degradation at $σ{=}0.4$ vs. 8.9% for YOLOv8m), outperforming YOLOv8m outright at $σ{=}0.6$, directly relevant to real-world FLS deployment.

发表机构

• University of California San Diego（加利福尼亚大学圣地亚哥分校）

机构由 AI 辅助整理，请以论文原文为准。