构建达卡高分辨率地表覆盖图，助力城市化研究
BD Open LULC Map: High-resolution land use land cover mapping & benchmarking for urban development in Dhaka, Bangladesh
- 用2.22米分辨率卫星图生成达卡及周边4392平方公里标注数据
- 三阶段专家验证确保数据可信，涵盖11类地表覆盖
- 支持深度学习模型训练与跨域适应，填补南亚数据空白
利用深度学习进行地表覆盖（LULC）制图可显著提升分类可靠性，有助于理解地理、社会经济状况、贫困水平和城市扩张。然而，由于资金有限、基础设施多样且人口密集，南亚/东亚发展中国家的标注卫星数据严重缺乏。本文提出BD Open LULC Map（BOLM），基于2.22米/像素的高分辨率必应卫星影像，为达卡大都市区及其周边地区提供像素级地表覆盖标注，共覆盖11个类别（如农田、水域、森林、城市结构、乡村聚落等），总面积达4,392平方公里（8.91亿像素）。通过三阶段地理信息系统专家流程完成地面真值验证。我们以DeepLab V3+模型在五个主要类别上进行基准测试，并对比必应与哨兵-2A影像的表现。BOLM旨在支持可靠深度学习模型与领域自适应任务，解决南亚/东亚关键地表覆盖数据集缺口问题。
原文摘要 · Abstract (English)
Land Use Land Cover (LULC) mapping using deep learning significantly enhances the reliability of LULC classification, aiding in understanding geography, socioeconomic conditions, poverty levels, and urban sprawl. However, the scarcity of annotated satellite data, especially in South/East Asian developing countries, poses a major challenge due to limited funding, diverse infrastructures, and dense populations. In this work, we introduce the BD Open LULC Map (BOLM), providing pixel-wise LULC annotations across eleven classes (e.g., Farmland, Water, Forest, Urban Structure, Rural Built-Up) for Dhaka metropolitan city and its surroundings using high-resolution Bing satellite imagery (2.22 m/pixel). BOLM spans 4,392 sq km (891 million pixels), with ground truth validated through a three-stage process involving GIS experts. We benchmark LULC segmentation using DeepLab V3+ across five major classes and compare performance on Bing and Sentinel-2A imagery. BOLM aims to support reliable deep models and domain adaptation tasks, addressing critical LULC dataset gaps in South/East Asia.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。