{"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/ev-segnet-semantic-segmentation-for-event","title":"EV-SegNet: Semantic Segmentation for Event-based Cameras","arxiv_id":"1811.12039","date":"2018-11-29","proceeding":null,"authors":["Iñigo Alonso","Ana C. Murillo"],"abstract":"Event cameras, or Dynamic Vision Sensor (DVS), are very promising sensors\nwhich have shown several advantages over frame based cameras. However, most\nrecent work on real applications of these cameras is focused on 3D\nreconstruction and 6-DOF camera tracking. Deep learning based approaches, which\nare leading the state-of-the-art in visual recognition tasks, could potentially\ntake advantage of the benefits of DVS, but some adaptations are needed still\nneeded in order to effectively work on these cameras. This work introduces a\nfirst baseline for semantic segmentation with this kind of data. We build a\nsemantic segmentation CNN based on state-of-the-art techniques which takes\nevent information as the only input. Besides, we propose a novel representation\nfor DVS data that outperforms previously used event representations for related\ntasks. Since there is no existing labeled dataset for this task, we propose how\nto automatically generate approximated semantic segmentation labels for some\nsequences of the DDD17 dataset, which we publish together with the model, and\ndemonstrate they are valid to train a model for DVS data only. We compare our\nresults on semantic segmentation from DVS data with results using corresponding\ngrayscale images, demonstrating how they are complementary and worth combining.","url_abs":"http://arxiv.org/abs/1811.12039v1","url_pdf":"http://arxiv.org/pdf/1811.12039v1.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":[],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-ddd17","task":"Semantic Segmentation","dataset":"DDD17","model":"EV-SegNet","rank_in_archive_order":9,"of":9,"metrics":{"mIoU":"54.81"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dsec","task":"Semantic Segmentation","dataset":"DSEC","model":"EV-SegNet","rank_in_archive_order":8,"of":9,"metrics":{"mIoU":"51.76"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.12039","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}