RopeBEV:鸟瞰式多摄像头路边感知网络

Jinrang Jia, Guangqi Yi, Yifeng Shi
{"title":"RopeBEV:鸟瞰式多摄像头路边感知网络","authors":"Jinrang Jia, Guangqi Yi, Yifeng Shi","doi":"arxiv-2409.11706","DOIUrl":null,"url":null,"abstract":"Multi-camera perception methods in Bird's-Eye-View (BEV) have gained wide\napplication in autonomous driving. However, due to the differences between\nroadside and vehicle-side scenarios, there currently lacks a multi-camera BEV\nsolution in roadside. This paper systematically analyzes the key challenges in\nmulti-camera BEV perception for roadside scenarios compared to vehicle-side.\nThese challenges include the diversity in camera poses, the uncertainty in\nCamera numbers, the sparsity in perception regions, and the ambiguity in\norientation angles. In response, we introduce RopeBEV, the first dense\nmulti-camera BEV approach. RopeBEV introduces BEV augmentation to address the\ntraining balance issues caused by diverse camera poses. By incorporating\nCamMask and ROIMask (Region of Interest Mask), it supports variable camera\nnumbers and sparse perception, respectively. Finally, camera rotation embedding\nis utilized to resolve orientation ambiguity. Our method ranks 1st on the\nreal-world highway dataset RoScenes and demonstrates its practical value on a\nprivate urban dataset that covers more than 50 intersections and 600 cameras.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"RopeBEV: A Multi-Camera Roadside Perception Network in Bird's-Eye-View\",\"authors\":\"Jinrang Jia, Guangqi Yi, Yifeng Shi\",\"doi\":\"arxiv-2409.11706\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multi-camera perception methods in Bird's-Eye-View (BEV) have gained wide\\napplication in autonomous driving. However, due to the differences between\\nroadside and vehicle-side scenarios, there currently lacks a multi-camera BEV\\nsolution in roadside. This paper systematically analyzes the key challenges in\\nmulti-camera BEV perception for roadside scenarios compared to vehicle-side.\\nThese challenges include the diversity in camera poses, the uncertainty in\\nCamera numbers, the sparsity in perception regions, and the ambiguity in\\norientation angles. In response, we introduce RopeBEV, the first dense\\nmulti-camera BEV approach. RopeBEV introduces BEV augmentation to address the\\ntraining balance issues caused by diverse camera poses. By incorporating\\nCamMask and ROIMask (Region of Interest Mask), it supports variable camera\\nnumbers and sparse perception, respectively. Finally, camera rotation embedding\\nis utilized to resolve orientation ambiguity. Our method ranks 1st on the\\nreal-world highway dataset RoScenes and demonstrates its practical value on a\\nprivate urban dataset that covers more than 50 intersections and 600 cameras.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11706\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11706","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

鸟瞰(BEV)多摄像头感知方法在自动驾驶中得到了广泛应用。然而,由于路侧和车侧场景的不同,目前还缺乏路侧多摄像头 BEV 解决方案。本文系统分析了路边场景多摄像头 BEV 感知与车侧场景相比所面临的主要挑战,包括摄像头姿态的多样性、摄像头数量的不确定性、感知区域的稀疏性以及方向角的模糊性。为此,我们推出了首款密集多摄像头 BEV 方法 RopeBEV。RopeBEV 引入了 BEV 增强技术,以解决不同摄像机姿势造成的训练平衡问题。通过结合摄像头掩码(CamMask)和感兴趣区域掩码(ROIMask),它分别支持可变摄像头数量和稀疏感知。最后,利用摄像头旋转嵌入来解决方向模糊问题。我们的方法在真实世界高速公路数据集 RoScenes 上排名第一,并在涵盖 50 多个交叉路口和 600 多个摄像头的私人城市数据集上证明了其实用价值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
RopeBEV: A Multi-Camera Roadside Perception Network in Bird's-Eye-View
Multi-camera perception methods in Bird's-Eye-View (BEV) have gained wide application in autonomous driving. However, due to the differences between roadside and vehicle-side scenarios, there currently lacks a multi-camera BEV solution in roadside. This paper systematically analyzes the key challenges in multi-camera BEV perception for roadside scenarios compared to vehicle-side. These challenges include the diversity in camera poses, the uncertainty in Camera numbers, the sparsity in perception regions, and the ambiguity in orientation angles. In response, we introduce RopeBEV, the first dense multi-camera BEV approach. RopeBEV introduces BEV augmentation to address the training balance issues caused by diverse camera poses. By incorporating CamMask and ROIMask (Region of Interest Mask), it supports variable camera numbers and sparse perception, respectively. Finally, camera rotation embedding is utilized to resolve orientation ambiguity. Our method ranks 1st on the real-world highway dataset RoScenes and demonstrates its practical value on a private urban dataset that covers more than 50 intersections and 600 cameras.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:481959085
Book学术官方微信