AZFP論文：使用U-Net神經網絡對AZFP多頻魚類浮游動物剖面儀回波圖中的鯡魚、鮭魚和氣泡進行分類
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：漁業和海洋觀測站使用回聲測深儀，但需要大量的人工努力才能在多頻回聲圖中對感興趣的物種進行分類。本文研究了使用改進的U-Net卷積神經網絡對回聲圖像中的生物和物理數據進行像素級分類，對鯡魚和鮭魚魚群、氣泡和海面進行準確分類。在加拿大不列顛哥倫比亞省海岸，使用聲學浮游動物和魚類剖面儀在四個頻率（67、125、200、455 kHz）上收集了兩年多的數據。此外，模擬數據（水深和太陽仰角）提供了空間和時間背景，以提高預測的質量。在訓練和分類過程中，通過使用平鋪策略將冗余構建到模型中。在訓練過程中，使用有限的一組帶注釋的數據，平移增強對U-Net進行編碼，使其具有強大的功能，能夠應用于替代部署配置（較低的采樣率或替代水深）。為了確保廣泛的適用性，這些網絡經過訓練，可以對噪聲保持不變的回聲圖進行分類。表現最佳的模型對鯡魚、鮭魚和氣泡類進行了分類，F1得分分別為93.0%、87.3%和86.5%。即使多個類別非常接近，結果也是準確的，因此保留了由于表面氣泡噪聲而被丟棄的生物數據。
