用于水下海底海带林分割的深度学习架构比较评估（基于Kelp-o-Tron）
Comparative Assessment of Deep Learning Architectures for Underwater Subsurface Kelp Forest Segmentation with The Kelp-o-Tron
AI总结：
该研究评估三种深度学习分割框架对水下海带林的分割性能，发现ResNet50-DeepLabV3（即Kelp-O-Tron）在准确率、鲁棒性和泛化性上表现最优，相关资源可用于水下生境制图与生态监测。
AI中文摘要：
水下海带林是重要的海岸生态系统，支撑着海洋生物多样性和生态系统动态，但由于光学退化、光照变化、水体浑浊度、植被重叠以及复杂的底栖背景，准确的水下海带分割仍具挑战性。我们系统评估了三种深度学习语义分割框架——ResNet34-U-Net、ResNet50-DeepLabV3和混合ResNet50-ASPP-Transformer架构——使用从美国东北海岸水域收集的高分辨率水下RGB图像进行海带检测。开发了包含3395对经SSeg辅助标注的图像-掩码的数据集，用于模型训练和验证，同时采用地理独立站点进行定量和定性评估。所有模型使用一致的预处理、数据增强和评估协议。在独立测试数据上，ResNet50-DeepLabV3取得最高的Dice系数（0.7120）和交并比（IoU；0.6267），其次是ResNet34-U-Net（Dice系数0.6868；IoU 0.5978）；混合ASPP-Transformer取得最高的像素准确率（0.8528），但Dice系数（0.6437）和IoU（0.5746）较低。外部定性评估进一步显示，DeepLabV3在不同环境条件、图像质量和底栖生境下能产生更一致的分割结果。总体而言，被命名为Kelp-O-Tron的ResNet50-DeepLabV3在分割准确率、鲁棒性和泛化性方面取得最佳平衡。该数据集、标注工作流和比较评估为推进自动化水下生境制图和生态监测提供了资源。
英文摘要：
Submerged kelp forests are vital coastal ecosystems that support marine biodiversity and ecosystem dynamics, yet accurate underwater kelp segmentation remains challenging due to optical degradation, illumination variability, turbidity, overlapping vegetation, and complex benthic backgrounds. We systematically evaluated three deep learning semantic segmentation frameworks, ResNet34-U-Net, ResNet50-DeepLabV3, and a hybrid ResNet50-ASPP-Transformer architecture, for kelp detection using high-resolution underwater RGB imagery collected from northeastern U.S. coastal waters. A dataset of 3,395 SSeg assisted annotated image-mask pairs was developed for model training and validation, while geographically independent sites were used for quantitative and qualitative evaluation. All models used consistent preprocessing, augmentation, and evaluation protocols. On independent test data, ResNet50-DeepLabV3 achieved the highest Dice (0.7120) and Intersection over Union (IoU; 0.6267), followed by ResNet34 U Net (Dice 0.6868; IoU 0.5978). The hybrid ASPP Transformer achieved the highest pixel accuracy (0.8528) but lower Dice (0.6437) and IoU (0.5746). External qualitative evaluation further showed that DeepLabV3 produced more consistent segmentation across varying environmental conditions, image qualities, and benthic habitats. Overall, ResNet50-DeepLabV3, termed Kelp-O-Tron, provided the best balance of segmentation accuracy, robustness, and generalization. The dataset, annotation workflow, and comparative evaluation provide resources for advancing automated underwater habitat mapping and ecological monitoring.
