arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.11319cs.CV
收藏

使用神经形态硬件的卫星图像低功耗船舶检测

Low-power Ship Detection in Satellite Images Using Neuromorphic Hardware

Neurobus(纽巴斯公司);BrainChip(脑芯片公司)

Gregor Lenz, Douglas McLelland

AI总结:

本文提出一种低功耗两级船舶检测系统,先用 Akida 1.0 神经形态硬件上的轻量二分类器筛选含船图像,再用 YOLOv5 精确定位,将 Jetson Nano 能耗从111.4 kJ降至27.3 kJ,同时保持76.9%的mAP。

摘要:

将地球观测图像数据从卫星传输到地面站在功率和带宽方面会产生显著成本。对于海上船舶检测,星载数据处理可以识别船舶并减少发送到地面的数据量。然而,星上捕获的大多数图像仅包含水体或陆地,Airbus Ship Detection 数据集显示只有22.1%的图像包含船舶。我们设计了一个低功耗的两级系统来优化性能,而不是依赖单一复杂模型。第一阶段是一个轻量级二分类器,作为门控机制来检测船舶是否存在。该阶段运行在 Brainchip 的 Akida 1.0 上,利用激活稀疏性来最小化动态功耗。第二阶段采用 YOLOv5 目标检测模型来识别船舶的位置和大小。该方法实现了76.9%的平均精度均值(mAP),当仅在包含船舶的图像上评估时,通过减少假阳性,该指标提高到79.3%。此外,我们计算出在 NVIDIA Jetson Nano 设备上评估完整验证集需要111.4 kJ的能量。我们的两级系统将这一能耗降低到27.3 kJ,不到四分之一,展示了异构计算系统的效率。

英文摘要:

Transmitting Earth observation image data from satellites to ground stations incurs significant costs in terms of power and bandwidth. For maritime ship detection, on-board data processing can identify ships and reduce the amount of data sent to the ground. However, most images captured on board contain only bodies of water or land, with the Airbus Ship Detection dataset showing only 22.1\% of images containing ships. We designed a low-power, two-stage system to optimize performance instead of relying on a single complex model. The first stage is a lightweight binary classifier that acts as a gating mechanism to detect the presence of ships. This stage runs on Brainchip's Akida 1.0, which leverages activation sparsity to minimize dynamic power consumption. The second stage employs a YOLOv5 object detection model to identify the location and size of ships. This approach achieves a mean Average Precision (mAP) of 76.9\%, which increases to 79.3\% when evaluated solely on images containing ships, by reducing false positives. Additionally, we calculated that evaluating the full validation set on a NVIDIA Jetson Nano device requires 111.4 kJ of energy. Our two-stage system reduces this energy consumption to 27.3 kJ, which is less than a fourth, demonstrating the efficiency of a heterogeneous computing system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑