{"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/hats-histograms-of-averaged-time-surfaces-for","title":"HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification","arxiv_id":"1803.07913","date":"2018-03-21","proceeding":"CVPR 2018 6","authors":["Amos Sironi","Manuele Brambilla","Nicolas Bourdis","Xavier Lagorce","Ryad Benosman"],"abstract":"Event-based cameras have recently drawn the attention of the Computer Vision\ncommunity thanks to their advantages in terms of high temporal resolution, low\npower consumption and high dynamic range, compared to traditional frame-based\ncameras. These properties make event-based cameras an ideal choice for\nautonomous vehicles, robot navigation or UAV vision, among others. However, the\naccuracy of event-based object classification algorithms, which is of crucial\nimportance for any reliable system working in real-world conditions, is still\nfar behind their frame-based counterparts. Two main reasons for this\nperformance gap are: 1. The lack of effective low-level representations and\narchitectures for event-based object classification and 2. The absence of large\nreal-world event-based datasets. In this paper we address both problems. First,\nwe introduce a novel event-based feature representation together with a new\nmachine learning architecture. Compared to previous approaches, we use local\nmemory units to efficiently leverage past temporal information and build a\nrobust event-based representation. Second, we release the first large\nreal-world event-based dataset for object classification. We compare our method\nto the state-of-the-art with extensive experiments, showing better\nclassification performance and real-time computation.","url_abs":"http://arxiv.org/abs/1803.07913v1","url_pdf":"http://arxiv.org/pdf/1803.07913v1.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":"hats-histograms-of-averaged-time-surfaces-for","repo_url":"https://github.com/fabhertz95/HATS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"robot-navigation","task_name":"Robot Navigation"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[],"datasets_introduced":[{"slug":"n-cars","name":"N-CARS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.07913","atlas_url":"https://app.syntology.ai/?focus=1803.07913","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}