单目视觉里程计的闭环检测:深度学习方法比较

2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) Pub Date : 2019-11-01 DOI:10.1109/SITIS.2019.00083

Mohamed Ali Sedrine, Wided Souidène Mseddi, T. Abdellatif, Rabah Attia

{"title":"单目视觉里程计的闭环检测:深度学习方法比较","authors":"Mohamed Ali Sedrine, Wided Souidène Mseddi, T. Abdellatif, Rabah Attia","doi":"10.1109/SITIS.2019.00083","DOIUrl":null,"url":null,"abstract":"In order to decrease monocular visual odometry drift by detecting loop closure, this paper presents a comparison between state of the art, 2-channel and Siamese, Convolutional Neural Networks. The work consists of training these networks in order to make them able to robustly identify loop closures. As we are in the case of having two input images, we perform our trainings and tests on both 2-channel and Siamese architecture for each network.","PeriodicalId":301876,"journal":{"name":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Loop Closure Detection for Monocular Visual Odometry: Deep-Learning Approaches Comparison\",\"authors\":\"Mohamed Ali Sedrine, Wided Souidène Mseddi, T. Abdellatif, Rabah Attia\",\"doi\":\"10.1109/SITIS.2019.00083\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In order to decrease monocular visual odometry drift by detecting loop closure, this paper presents a comparison between state of the art, 2-channel and Siamese, Convolutional Neural Networks. The work consists of training these networks in order to make them able to robustly identify loop closures. As we are in the case of having two input images, we perform our trainings and tests on both 2-channel and Siamese architecture for each network.\",\"PeriodicalId\":301876,\"journal\":{\"name\":\"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SITIS.2019.00083\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SITIS.2019.00083","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

为了通过检测环路闭合来减少单目视觉里程计漂移，本文对目前最先进的2通道卷积神经网络和Siamese卷积神经网络进行了比较。这项工作包括训练这些网络，使它们能够鲁棒地识别闭环。由于我们在有两个输入图像的情况下，我们对每个网络在2通道和Siamese架构上执行训练和测试。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Loop Closure Detection for Monocular Visual Odometry: Deep-Learning Approaches Comparison

In order to decrease monocular visual odometry drift by detecting loop closure, this paper presents a comparison between state of the art, 2-channel and Siamese, Convolutional Neural Networks. The work consists of training these networks in order to make them able to robustly identify loop closures. As we are in the case of having two input images, we perform our trainings and tests on both 2-channel and Siamese architecture for each network.

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

2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)

自引率

0.00%

发文量