Detecting Every Object From Events

IF 18.6
Haitian Zhang;Chang Xu;Xinya Wang;Bingde Liu;Guang Hua;Lei Yu;Wen Yang
{"title":"Detecting Every Object From Events","authors":"Haitian Zhang;Chang Xu;Xinya Wang;Bingde Liu;Guang Hua;Lei Yu;Wen Yang","doi":"10.1109/TPAMI.2025.3565102","DOIUrl":null,"url":null,"abstract":"Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly rely on RGB cameras, but these frame-based sensors usually have high latency and limited dynamic range, leading to safety risks under extreme conditions like fast-moving objects, overexposure, and darkness. In this study, we turn to the event-based vision, featured by its sub-millisecond latency and high dynamic range, for robust CAOD. We propose Detecting Every Object in Events (DEOE), an approach aimed at achieving high-speed, class-agnostic object detection in event-based vision. Built upon the fast event-based backbone: recurrent vision transformer, we jointly consider the spatial and temporal consistencies to identify potential objects. The discovered potential objects are assimilated as soft positive samples to avoid being suppressed as backgrounds. Moreover, we introduce a disentangled objectness head to separate the foreground-background classification and novel object discovery tasks, enhancing the model's generalization in localizing novel objects while maintaining a strong ability to filter out the background. Extensive experiments confirm the superiority of our proposed DEOE in both open-set and closed-set settings, outperforming strong baseline methods.","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"47 8","pages":"7171-7178"},"PeriodicalIF":18.6000,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10979499/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly rely on RGB cameras, but these frame-based sensors usually have high latency and limited dynamic range, leading to safety risks under extreme conditions like fast-moving objects, overexposure, and darkness. In this study, we turn to the event-based vision, featured by its sub-millisecond latency and high dynamic range, for robust CAOD. We propose Detecting Every Object in Events (DEOE), an approach aimed at achieving high-speed, class-agnostic object detection in event-based vision. Built upon the fast event-based backbone: recurrent vision transformer, we jointly consider the spatial and temporal consistencies to identify potential objects. The discovered potential objects are assimilated as soft positive samples to avoid being suppressed as backgrounds. Moreover, we introduce a disentangled objectness head to separate the foreground-background classification and novel object discovery tasks, enhancing the model's generalization in localizing novel objects while maintaining a strong ability to filter out the background. Extensive experiments confirm the superiority of our proposed DEOE in both open-set and closed-set settings, outperforming strong baseline methods.
从事件中检测每个对象
物体检测在自动驾驶中至关重要,定位未知类别的物体更实用,但也更具挑战性:这是一项被称为“类别未知物体检测”(Class-Agnostic Object detection, CAOD)的努力。现有的cad研究主要依赖于RGB相机,但这些基于帧的传感器通常具有高延迟和有限的动态范围,在快速移动的物体、过度曝光和黑暗等极端条件下存在安全风险。在本研究中,我们转向基于事件的视觉,其特点是其亚毫秒延迟和高动态范围,以实现鲁棒的cad。我们提出了一种在基于事件的视觉中实现高速、类别无关的对象检测的方法——事件中检测每个对象(DEOE)。在基于事件的快速主干:循环视觉转换器的基础上,我们联合考虑空间和时间的一致性来识别潜在的目标。发现的潜在目标被同化为软阳性样本,以避免作为背景被抑制。此外,我们引入了解纠缠的目标头来分离前景-背景分类和新目标发现任务,增强了模型在定位新目标时的泛化能力,同时保持了较强的背景过滤能力。大量的实验证实了我们提出的DEOE在开集和闭集设置中的优越性,优于强基线方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信