AZFP论文：使用U-Net神经网络对AZFP多频鱼类浮游动物剖面仪回波图中的鲱鱼、鲑鱼和气泡进行分类
Abstract: Echosounders are used by fisheries and ocean observatories, but significant manual effort is required to classify species of interest within multifrequency echograms. This article investigates the use of modified U-Net convolutional neural networks for the pixel-level classification of biological and physical data in echogram images with accurate classification of herring and salmon schools, bubbles, and the sea surface. Data were collected on the coast of British Columbia, Canada, over two years using an Acoustic Zooplankton and Fish Profiler at four frequencies (67, 125, 200, 455 kHz). In addition, simulated data (water depth and solar elevation angle) provide spatial and temporal context to improve the quality of predictions. Redundancy is built into the model by using a tiling strategy during training and classification. During training, using a limited set of annotated data, translational augmentation encodes the U-Nets with robust features that enable applications for alternate deployment configurations (lower sampling rates or alternate water depths). To ensure broad applicability, these networks were trained to classify echograms with noise left intact. The best-performing model classifies herring, salmon, and bubble classes with F1 scores of 93.0%, 87.3%, and 86.5%, respectively. The results are accurate even when multiple classes are in close proximity, thus, retaining biological data that would otherwise be discarded due to surface bubble noise.
摘要：渔业和海洋观测站使用回声测深仪，但需要大量的人工努力才能在多频回声图中对感兴趣的物种进行分类。本文研究了使用改进的U-Net卷积神经网络对回声图像中的生物和物理数据进行像素级分类，对鲱鱼和鲑鱼鱼群、气泡和海面进行准确分类。在加拿大不列颠哥伦比亚省海岸，使用声学浮游动物和鱼类剖面仪在四个频率（67、125、200、455 kHz）上收集了两年多的数据。此外，模拟数据（水深和太阳仰角）提供了空间和时间背景，以提高预测的质量。在训练和分类过程中，通过使用平铺策略将冗余构建到模型中。在训练过程中，使用有限的一组带注释的数据，平移增强对U-Net进行编码，使其具有强大的功能，能够应用于替代部署配置（较低的采样率或替代水深）。为了确保广泛的适用性，这些网络经过训练，可以对噪声保持不变的回声图进行分类。表现最佳的模型对鲱鱼、鲑鱼和气泡类进行了分类，F1得分分别为93.0%、87.3%和86.5%。即使多个类别非常接近，结果也是准确的，因此保留了由于表面气泡噪声而被丢弃的生物数据。
