{"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/increasing-the-sentinel-2-potential-for","title":"Increasing the Sentinel-2 potential for marine plastic litter monitoring through image fusion techniques","arxiv_id":null,"date":"2020-07-30","proceeding":"Marine Pollution Bulletin 2022","authors":["Maria Kremezi","Viktoria Kristollari","Vassilia Karathanassi","Konstantinos Topouzelis","Pol Kolokoussis","Nicolò Taggio","Antonello Aiello","Giulio Ceriola","Enrico Barbone","Paolo Corradi"],"abstract":"Sentinel-2 (S2) images have been used in several projects to detect large accumulations of marine litter and plastic targets. Their limited spatial resolution though hinders the detection of relatively small floating accumulations of marine debris. Thus, this study aims at overcoming this limit through the exploration of fusion with very high-resolution WorldView-2/3 (WV-2/3) images. Various state-of-the-art approaches (component substitution, spectral unmixing, deep learning) were applied on data collected in synchronized acquisitions of plastic targets of various sizes and materials in seawater. The fused images were evaluated for spectral and spatial distortions, as well as their ability to spectrally discriminate plastics from water. Several WV-2/3 band combinations were investigated and five litter indexes were applied. Results showed that: a) the VNIR combination is the optimal one, b) the smallest observable plastic target is 0.6 × 0.6 m2 and c) SWIR bands are important for marine litter detection.","url_abs":"https://www.sciencedirect.com/science/article/pii/S0025326X22006567","url_pdf":"http://users.ntua.gr/vkristoll/assets/MBP_paper_preprint.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":"increasing-the-sentinel-2-potential-for","repo_url":"https://github.com/vkristoll/Fusion-Sentinel2-Worldview","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"srgan","method_name":"SRGAN"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}