SealNet 2.0: Human-Level Fully-Automated Pack-Ice Seal Detection in Very-High-Resolution Satellite Imagery with CNN Model Ensembles
SealNet 2.0: Human-Level Fully-Automated Pack-Ice Seal Detection in Very-High-Resolution Satellite Imagery with CNN Model Ensembles
复制标题
DOI：
10.3390/rs14225655
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
B. Gonçalves;M. Wethington;H. Lynch
中科院分区：
文献类型：
--
作者：
B. Gonçalves;M. Wethington;H. Lynch
浮冰海豹是南大洋的主要指示物种。它们的大小(2-4米)和分布在整个大陆上，使它们成为通过非常高分辨率的卫星图像进行监测的理想对象。然而，所需的图像数量太大，阻碍了我们仅依靠手动注释的能力。在这里，我们介绍了SealNet 2.0，这是一种完全自动化的海豹检测方法，它将海冰分割模型与用于海豹检测的语义分割卷积神经网络模型集成在一起来寻找潜在的海豹栖息地。我们最好的集成在样本外测试数据集上达到了0.806的准确率和0.640的召回率，超过了两个训练有素的人类观察者。在原始SealNet的基础上构建，它的表现优于其前身，它使用了仅专注于海冰的注释数据集，利用大量高性能计算资源的全面超参数研究，以及通过回归头部输出和预测密封位置的分段头部对数进行后处理。即使使用我们的集合模型的简化版本，使用人工智能预测作为指南，也极大地提高了两名人类专家的精确度和召回率，显示出作为新手海豹注释员培训工具的潜力。与人类观察者一样，我们的自动化方法的性能随着地形的崎岖而恶化，这突显了从人工智能输出中提取全球人口估计的统计处理的必要性。
Pack-ice seals are key indicator species in the Southern Ocean. Their large size (2–4 m) and continent-wide distribution make them ideal candidates for monitoring programs via very-high-resolution satellite imagery. The sheer volume of imagery required, however, hampers our ability to rely on manual annotation alone. Here, we present SealNet 2.0, a fully automated approach to seal detection that couples a sea ice segmentation model to find potential seal habitats with an ensemble of semantic segmentation convolutional neural network models for seal detection. Our best ensemble attains 0.806 precision and 0.640 recall on an out-of-sample test dataset, surpassing two trained human observers. Built upon the original SealNet, it outperforms its predecessor by using annotation datasets focused on sea ice only, a comprehensive hyperparameter study leveraging substantial high-performance computing resources, and post-processing through regression head outputs and segmentation head logits at predicted seal locations. Even with a simplified version of our ensemble model, using AI predictions as a guide dramatically boosted the precision and recall of two human experts, showing potential as a training device for novice seal annotators. Like human observers, the performance of our automated approach deteriorates with terrain ruggedness, highlighting the need for statistical treatment to draw global population estimates from AI output.