JellyNet: The convolutional neural network jellyfish bloom detector
JellyNet: The convolutional neural network jellyfish bloom detector
复制标题
DOI：
10.1016/j.jag.2020.102279
复制
发表时间：
2021-05-01
影响因子：
7.5
通讯作者：
Casado, Monica Rivas
中科院分区：
文献类型：
--
作者：
Mcilwaine, Ben;Casado, Monica Rivas
由于水母大量繁殖的威胁，沿海工业面临全球范围内的破坏。它们会摧毁沿海渔业并堵塞海水淡化厂和核电站的取水系统。这可能导致收入和电力输出的损失。本文介绍了 JellyNet：一种卷积神经网络 (CNN) 水母绽放检测模型，根据无人机 (UAV) 收集的高分辨率遥感图像进行训练。 JellyNet 提供早期（6-8 小时）水华预警系统的检测能力。 1539 张图像是从 2 个地点的航班收集的：英国 Croabh Haven 和加拿大 Pruth Bay。训练/测试数据集被手动标记，并分为两类：“存在开花”和“不存在开花”。使用 500 x 500 像素图像来增强水母水华的细粒度图案检测。使用 75/25% 的训练/测试分割完成模型测试，并在使用保留的验证数据集进行模型训练之前选择超参数。使用 VGG-16 架构的迁移学习和水母绽放特定的二元分类器的准确率超过了 90%。测试模型性能的峰值准确率达到 97.5%。本文展示了高分辨率、多传感器水华检测功能的第一个示例，具有来自两个海洋的集成鲁棒性，可应对现实世界的检测挑战。
Coastal industries face disruption on a global scale due to the threat of large blooms of jellyfish. They can decimate coastal fisheries and clog the water intake systems of desalination and nuclear power plants. This can lead to losses of revenue and power output. This paper presents JellyNet: a convolutional neural network (CNN) jellyfish bloom detection model trained on high resolution remote sensing imagery collected by unmanned aerial vehicles (UAVs). JellyNet provides the detection capability for an early (6-8 h) bloom warning system. 1539 images were collected from flights at 2 locations: Croabh Haven, UK and Pruth Bay, Canada. The training/test dataset was manually labelled, and split into two classes: 'Bloom present' and 'No bloom present'. 500 x 500 pixel images were used to increase fine-grained pattern detection of the jellyfish blooms. Model testing was completed using a 75/25% training/test split with hyperparameters selected prior to model training using a held-out validation dataset. Transfer learning using VGG-16 architecture, and a jellyfish bloom specific binary classifier surpassed an accuracy of 90%. Test model performance peaked at 97.5% accuracy. This paper exhibits the first example of a high resolution, multi-sensor jellyfish bloom detection capability, with integrated robustness from two oceans to tackle real world detection challenges.