此数据集是一个关于青藏高原的湖泊水体可见光谱谷歌地球遥感数据集，范围包含整个青藏高原，且是由RGB图像组成。此数据集共包含有6774张图像，大小为256* 256, DPI为96，深度为24。在此数据集中，只有湖泊(不包括河流、水库、池塘等)被注释，且所有的这些注释都是使用labelme进行标记。
", "ds_source": "谷歌地球。
", "ds_process_way": "为保证模型对样本的学习能力，我们将图像分割成不重叠的块，并使用数据平衡策略，若图像中负样本占比太高，则丢弃图像。
", "ds_quality": "256*256。
", "ds_acq_start_time": "2020-08-01 00:00:00", "ds_acq_end_time": "2020-08-31 00:00:00", "ds_acq_place": "青藏高原", "ds_acq_lon_east": 104.0, "ds_acq_lat_south": 26.0, "ds_acq_lon_west": 73.0, "ds_acq_lat_north": 39.0, "ds_acq_alt_low": 3000.0, "ds_acq_alt_high": 5000.0, "ds_share_type": "login-access", "ds_total_size": 545795453, "ds_files_count": 4, "ds_format": "", "ds_space_res": "17m", "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "b4d9fb27-ec93-433d-893a-2689379a3fc0.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "在使用数据时，请注明数据来自国家冰川冻土沙漠科学数据中心和兰州大学", "ds_from_station": null, "organization_id": "52b7b79b-860c-49a5-9083-9a70cf8bed5a", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 3, "publish_time": "2021-05-14 15:30:57", "last_updated": "2025-04-24 16:23:04", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.ncdc.NIEER.2021.1971", "i18n": { "en": { "title": "Qinghai-Tibet Plateau Lake Semantic Segmentation Dataset", "ds_format": "", "ds_source": "Google Earth.
", "ds_quality": "256*256.
", "ds_ref_way": "", "ds_abstract": "This dataset is a visible-spectrum Google Earth remote sensing dataset of lake water bodies on the Qinghai-Tibet Plateau, covering the entire plateau region and composed of RGB images. It contains 6,774 images with a resolution of 256×256 pixels, 96 DPI, and 24-bit depth. In this dataset, only lakes (excluding rivers, reservoirs, ponds, etc.) are annotated, and all annotations were labeled using the labelme tool.\n
", "ds_time_res": "", "ds_acq_place": "Qinghai-Tibet Plateau", "ds_space_res": "17m", "ds_projection": "", "ds_process_way": "To ensure the model's learning capability for samples, we divided the images into non-overlapping patches and applied a data balancing strategy. Images with excessively high proportions of negative samples were discarded.
", "ds_ref_instruction": "When using the data, please indicate that the data are from the national glacier, permafrost and desert scientific data center and Lanzhou University" } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "CC BY 4.0", "doi_reg_from": "reg_local", "cstr_reg_from": "reg_local", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "遥感", "语义分析", "青藏高原" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "青藏高原" ], "ds_time_tags": [ 2020 ], "ds_contributors": [ { "true_name": "王兆滨", "email": "wangzhb@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" }, { "true_name": "张耀南", "email": "yaonan@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" }, { "true_name": "高雄", "email": "xgao2019@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "王兆滨", "email": "wangzhb@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" }, { "true_name": "高雄", "email": "xgao2019@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "ds_managers": [ { "true_name": "王兆滨", "email": "wangzhb@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" }, { "true_name": "高雄", "email": "xgao2019@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "category": "基础地理" }