A fine-grained semantic segmentation dataset of marine aquaculture cages in Fujian Province, China (CC, SC, and DWC)
Abstract
本数据集是专门针对近海养殖网箱(Marine Aquaculture Cages)开发的精细化语义分割评估数据集 。数据集覆盖了中国福建省两个代表性的沿海区域:东山-诏安湾(密集养殖区)和湄洲湾(开放分散养殖区) 。数据集包含 0.5 米分辨率的 RGB 光学遥感影像,精细标注了三类主要网箱类型:传统木质网箱(Traditional cages, CC)、塑胶网箱(Suspended cages, SC)以及深海大网箱(Deep-water cages, DWC),并包含背景类 。标注过程结合了实地考察、高分辨率摄影和专家解译,并经过多轮质量控制,确保了类别的准确性和边界的精细度 。论文doi: 10.1080/10095020.2026.2719215 ;Github地址:llmn203/Deep-Learning-Models-for-Fine-grained-Semantic-Segmentation-of-Marine-Aquaculture-Cages。
Fields of Study & Subjects
Remote-Sensing Image Classification
Water Quality Monitoring Technologies
Marine Bivalve and Aquaculture Studies
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 11 February 2026
- Language
- ZH
- Document type
- Dataset