Multivariate Probabilistic Monocular 3D Object Detection

Xuepeng Shi, Zhixiang Chen, Tae-Kyun Kim
{"title":"Multivariate Probabilistic Monocular 3D Object Detection","authors":"Xuepeng Shi, Zhixiang Chen, Tae-Kyun Kim","doi":"10.1109/WACV56688.2023.00426","DOIUrl":null,"url":null,"abstract":"In autonomous driving, monocular 3D object detection is an important but challenging task. Towards accurate monocular 3D object detection, some recent methods recover the distance of objects from the physical height and visual height of objects. Such decomposition framework can introduce explicit constraints on the distance prediction, thus improving its accuracy and robustness. However, the inaccurate physical height and visual height prediction still may exacerbate the inaccuracy of the distance prediction. In this paper, we improve the framework by multivariate probabilistic modeling. We explicitly model the joint probability distribution of the physical height and visual height. This is achieved by learning a full covariance matrix of the physical height and visual height during training, with the guide of a multivariate likelihood. Such explicit joint probability distribution modeling not only leads to robust distance prediction when both the predicted physical height and visual height are inaccurate, but also brings learned covariance matrices with expected behaviors. The experimental results on the challenging Waymo Open and KITTI datasets show the effectiveness of our framework1.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACV56688.2023.00426","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

In autonomous driving, monocular 3D object detection is an important but challenging task. Towards accurate monocular 3D object detection, some recent methods recover the distance of objects from the physical height and visual height of objects. Such decomposition framework can introduce explicit constraints on the distance prediction, thus improving its accuracy and robustness. However, the inaccurate physical height and visual height prediction still may exacerbate the inaccuracy of the distance prediction. In this paper, we improve the framework by multivariate probabilistic modeling. We explicitly model the joint probability distribution of the physical height and visual height. This is achieved by learning a full covariance matrix of the physical height and visual height during training, with the guide of a multivariate likelihood. Such explicit joint probability distribution modeling not only leads to robust distance prediction when both the predicted physical height and visual height are inaccurate, but also brings learned covariance matrices with expected behaviors. The experimental results on the challenging Waymo Open and KITTI datasets show the effectiveness of our framework1.
多元概率单目三维目标检测
在自动驾驶中,单目三维目标检测是一项重要但具有挑战性的任务。为了实现精确的单目三维目标检测,最近的一些方法是从物体的物理高度和视觉高度恢复物体的距离。这种分解框架可以对距离预测引入明确的约束,从而提高了预测的准确性和鲁棒性。然而,物理高度和视觉高度预测的不准确仍然会加剧距离预测的不准确性。在本文中,我们通过多元概率建模对框架进行了改进。我们明确地建立了物理高度和视觉高度的联合概率分布模型。这是通过在训练期间学习物理高度和视觉高度的完整协方差矩阵,在多元似然的指导下实现的。这种显式的联合概率分布建模不仅可以在预测的物理高度和视觉高度都不准确的情况下实现鲁棒的距离预测,而且可以带来具有预期行为的学习协方差矩阵。在具有挑战性的Waymo Open和KITTI数据集上的实验结果表明了我们的框架的有效性。
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:481959085
Book学术官方微信