{"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/destruction-from-sky-weakly-supervised","title":"Destruction from sky: Weakly supervised approach for destruction detection in satellite imagery","arxiv_id":null,"date":"2020-04-01","proceeding":"ISPRS Journal of Photogrammetry and Remote Sensing 2020 4","authors":["Muhammad Usman Ali","Waqas Sultani","Mohsen Ali"],"abstract":"Natural and man-made disasters cause huge damage to built infrastructures and results in loss of human lives. The rehabilitation efforts and rescue operations are hampered by the non-availability of accurate and timely information regarding the location of damaged infrastructure and its extent. In this paper, we model the destruction in satellite imagery using a deep learning model employing a weakly-supervised approach. In stark contrast to previous approaches, instead of solving the problem as change detection (using pre and post-event images), we model to identify destruction itself using a single post-event image. To overcome the challenge of collecting pixel-level ground truth data mostly used during training, we only assume image-level labels, representing either destruction is present (at any location) in a given image or not. The proposed attention-based mechanism learns to identify the image-patches with destruction automatically under the sparsity constraint. Furthermore, to reduce false-positive and improve segmentation quality, a hard negative mining technique has been proposed that results in considerable improvement over baseline. To validate our approach, we have collected a new dataset containing destruction and non-destruction images from Indonesia, Yemen, Japan, and Pakistan. On testing-dataset, we obtained excellent destruction results with pixel-level accuracy of 93% and patch level accuracy of 91%. The source code and dataset will be made publicly available.","url_abs":"http://im.itu.edu.pk/destruction-detection/","url_pdf":"http://im.itu.edu.pk/wp-content/uploads/2020/02/id_compressed.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":"destruction-from-sky-weakly-supervised","repo_url":"https://github.com/usmanali414/Destruction-Detection-in-Satellite-Imagery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"}],"methods":[],"datasets_introduced":[{"slug":"destruction","name":"destruction","full_name":"desctruction detection dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}