{"id":"60dac98d-eec4-41df-9ad5-b1563e5c532c","title":"中国90座城市建筑物屋顶矢量数据集（2020）","title_en":"Vectorized rooftop area data for 90 cities in China (2020)","serial":"","user_limit":"为尊重知识产权、保障数据作者的权益、扩展数据中心的服务、评估数据的应用潜力，请数据使用者在使用数据所产生的研究成果中（包括公开发表的论文、论著、数据产品和未公开发表的研究报告、数据产品等成果），明确注明数据来源和数据作者。对于转载（二次或多次发布）的数据，作者还须注明原始数据来源。","instructions":"China_90Cities_Rooftop_Data / Tiers X / YYY / YYY.shp\n该数据集文件格式为ESRI Shapefile 格式，Arcgis等专业软件均可直接打开","description":"该数据集包含中国90座城市（根据城市行政等级及区域分布综合选取，城市名录详见附件1）建筑物屋顶矢量数据。主要基于深度学习语义分割模型和多源遥感影像进行制作。首先，对原始影像进行预处理，并根据城市等级及其区域分布情况进行分层采样以及目视解译，制作训练和测试数据。然后将训练数据输入深度学习语义分割模型进行训练，使其适用于建筑物屋顶提取任务，并基于测试数据，采用深度学习领域结果评价一般性指标对建筑物屋顶提取模型性能进行评价。最后，将此模型应用于中国90座城市建筑屋顶提取任务中，自动提取建筑物屋顶并进行矢量化。该数据集可以为城市乃至全国尺度以建筑物屋顶为基础的相关研究（如屋顶太阳能潜力评估、城市规划等）提供重要数据支撑。","doi":"10.11888/Geogra.tpdc.271702","projection":"Albers","language":"zh","share_type":"online","east":135.05,"west":73.66,"south":3.86,"north":53.55,"scale":null,"crs":null,"filesize":143360.0,"share_policy":"a","ts_created":"2021-09-10T21:40:50.213268+08:00","doi_type":"沿用数据已有DOI","ts_updated":"2022-01-18T16:18:26.931916+08:00","time_description":"制作于2021年9月","datas_group":3,"time_description_en":"Produced in September 2021","data_format":null,"project":[11],"specials":[],"cite":null,"review_status":5,"review_invite":[],"review_editor":{"id":42421,"last_login":"2022-04-08T15:16:51.670544+08:00","username":"任慧霞","email":"510727846@qq.com","is_active":true,"is_staff":true,"user_name":"任慧霞"},"data_sources":null,"temporal_resolution":"1 year < x < 10 year","spatial_resolution":"<= 1 m","license":"Attribution 4.0 International (CC BY 4.0)","fund":[],"subtopics":{"metadata":"60dac98d-eec4-41df-9ad5-b1563e5c532c","three_pole":null,"third_pole":null},"username":"张锴","review_time":null,"protected_duration":null,"protected_describe":null,"is_important":false,"hit_count":538}