{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deepglobe-2018-a-challenge-to-parse-the-earth","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","arxiv_id":"1805.06561","date":"2018-05-17","proceeding":null,"authors":["Ilke Demir","Krzysztof Koperski","David Lindenbaum","Guan Pang","Jing Huang","Saikat Basu","Forest Hughes","Devis Tuia","Ramesh Raskar"],"abstract":"We present the DeepGlobe 2018 Satellite Image Understanding Challenge, which\nincludes three public competitions for segmentation, detection, and\nclassification tasks on satellite images. Similar to other challenges in\ncomputer vision domain such as DAVIS and COCO, DeepGlobe proposes three\ndatasets and corresponding evaluation methodologies, coherently bundled in\nthree competitions with a dedicated workshop co-located with CVPR 2018.\n  We observed that satellite imagery is a rich and structured source of\ninformation, yet it is less investigated than everyday images by computer\nvision researchers. However, bridging modern computer vision with remote\nsensing data analysis could have critical impact to the way we understand our\nenvironment and lead to major breakthroughs in global urban planning or climate\nchange research. Keeping such bridging objective in mind, DeepGlobe aims to\nbring together researchers from different domains to raise awareness of remote\nsensing in the computer vision community and vice-versa. We aim to improve and\nevaluate state-of-the-art satellite image understanding approaches, which can\nhopefully serve as reference benchmarks for future research in the same topic.\nIn this paper, we analyze characteristics of each dataset, define the\nevaluation criteria of the competitions, and provide baselines for each task.","url_abs":"http://arxiv.org/abs/1805.06561v1","url_pdf":"http://arxiv.org/pdf/1805.06561v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deepglobe-2018-a-challenge-to-parse-the-earth","repo_url":"https://github.com/chenwydj/ultra_high_resolution_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"deepglobe","name":"DeepGlobe","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06561","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}