基于两级局部双目BA和GPU的高性能视觉里程测量

2013 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2013-06-23 DOI:10.1109/IVS.2013.6629614

W. Lu, Z. Xiang, Jilin Liu

{"title":"基于两级局部双目BA和GPU的高性能视觉里程测量","authors":"W. Lu, Z. Xiang, Jilin Liu","doi":"10.1109/IVS.2013.6629614","DOIUrl":null,"url":null,"abstract":"Visual odometry becomes an important method to deal the localization work in intelligent vehicle and robotics. A high performance visual odometry needs to achieve two requirements: high accuracy and high frequency. So we propose a two-stage local binocular bundle adjustment algorithm doing the optimization and construct a parallel pipeline using GPU acceleration. Finally, our system can run at about 35~40 frames per second with the maximum RMS 3D localization error less than 1%.","PeriodicalId":251198,"journal":{"name":"2013 IEEE Intelligent Vehicles Symposium (IV)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"High-performance visual odometry with two-stage local binocular BA and GPU\",\"authors\":\"W. Lu, Z. Xiang, Jilin Liu\",\"doi\":\"10.1109/IVS.2013.6629614\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Visual odometry becomes an important method to deal the localization work in intelligent vehicle and robotics. A high performance visual odometry needs to achieve two requirements: high accuracy and high frequency. So we propose a two-stage local binocular bundle adjustment algorithm doing the optimization and construct a parallel pipeline using GPU acceleration. Finally, our system can run at about 35~40 frames per second with the maximum RMS 3D localization error less than 1%.\",\"PeriodicalId\":251198,\"journal\":{\"name\":\"2013 IEEE Intelligent Vehicles Symposium (IV)\",\"volume\":\"36 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE Intelligent Vehicles Symposium (IV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IVS.2013.6629614\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE Intelligent Vehicles Symposium (IV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVS.2013.6629614","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 27

摘要

视觉里程计已成为智能汽车和机器人中处理定位工作的重要方法。一个高性能的视觉里程计需要达到两个要求:高精度和高频率。为此，我们提出了一种两阶段双目局部束平差算法，并利用GPU加速构造了一个并行流水线。最后，我们的系统能够以35~40帧/秒的速度运行，最大RMS 3D定位误差小于1%。

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

High-performance visual odometry with two-stage local binocular BA and GPU

Visual odometry becomes an important method to deal the localization work in intelligent vehicle and robotics. A high performance visual odometry needs to achieve two requirements: high accuracy and high frequency. So we propose a two-stage local binocular bundle adjustment algorithm doing the optimization and construct a parallel pipeline using GPU acceleration. Finally, our system can run at about 35~40 frames per second with the maximum RMS 3D localization error less than 1%.

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

2013 IEEE Intelligent Vehicles Symposium (IV)

自引率

0.00%

发文量