FisheyeDistanceNet++: Self-Supervised Fisheye Distance Estimation with Self-Attention, Robust Loss Function and Camera View Generalization

V. Kumar, S. Yogamani, Stefan Milz, Patrick Mäder
{"title":"FisheyeDistanceNet++: Self-Supervised Fisheye Distance Estimation with Self-Attention, Robust Loss Function and Camera View Generalization","authors":"V. Kumar, S. Yogamani, Stefan Milz, Patrick Mäder","doi":"10.2352/issn.2470-1173.2021.17.avm-181","DOIUrl":null,"url":null,"abstract":"\n FisheyeDistanceNet [1] proposed a self-supervised monocular depth estimation method for fisheye cameras with a large field of view (> 180°). To achieve scale-invariant depth estimation, FisheyeDistanceNet supervises depth map predictions over multiple scales during training.\n To overcome this bottleneck, we incorporate self-attention layers and robust loss function [2] to FisheyeDistanceNet. A general adaptive robust loss function helps obtain sharp depth maps without a need to train over multiple scales and allows us to learn hyperparameters in loss function to\n aid in better optimization in terms of convergence speed and accuracy. We also ablate the importance of Instance Normalization over Batch Normalization in the network architecture. Finally, we generalize the network to be invariant to camera views by training multiple perspectives using front,\n rear, and side cameras. Proposed algorithm improvements, FisheyeDistanceNet++, result in 30% relative improvement in RMSE while reducing the training time by 25% on the WoodScape dataset. We also obtain state-of-the-art results on the KITTI dataset, in comparison to other self-supervised monocular\n methods.\n","PeriodicalId":177462,"journal":{"name":"Autonomous Vehicles and Machines","volume":"125 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Autonomous Vehicles and Machines","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2352/issn.2470-1173.2021.17.avm-181","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

Abstract

FisheyeDistanceNet [1] proposed a self-supervised monocular depth estimation method for fisheye cameras with a large field of view (> 180°). To achieve scale-invariant depth estimation, FisheyeDistanceNet supervises depth map predictions over multiple scales during training. To overcome this bottleneck, we incorporate self-attention layers and robust loss function [2] to FisheyeDistanceNet. A general adaptive robust loss function helps obtain sharp depth maps without a need to train over multiple scales and allows us to learn hyperparameters in loss function to aid in better optimization in terms of convergence speed and accuracy. We also ablate the importance of Instance Normalization over Batch Normalization in the network architecture. Finally, we generalize the network to be invariant to camera views by training multiple perspectives using front, rear, and side cameras. Proposed algorithm improvements, FisheyeDistanceNet++, result in 30% relative improvement in RMSE while reducing the training time by 25% on the WoodScape dataset. We also obtain state-of-the-art results on the KITTI dataset, in comparison to other self-supervised monocular methods.
fishheyedistancenet++:自关注、鲁棒损失函数和相机视图泛化的自监督鱼眼距离估计
fishheyedistancenet[1]针对大视场(> 180°)的鱼眼相机提出了一种自监督单眼深度估计方法。为了实现尺度不变的深度估计,fishheyedistancenet在训练期间监督多个尺度的深度图预测。为了克服这一瓶颈,我们将自关注层和鲁棒损失函数[2]结合到fishheyedistancenet中。一个通用的自适应鲁棒损失函数有助于获得清晰的深度图,而不需要在多个尺度上进行训练,并允许我们学习损失函数中的超参数,以帮助在收敛速度和精度方面更好地优化。在网络架构中,实例规范化比批处理规范化更重要。最后,我们通过使用前置、后置和侧置摄像头训练多个视角,使网络对摄像头视图保持不变。提出的算法改进fishheyedistancenet ++在WoodScape数据集上的RMSE相对提高了30%,同时减少了25%的训练时间。与其他自监督单目方法相比,我们还在KITTI数据集上获得了最先进的结果。
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