Large-scale Structure-from-Motion Reconstruction with small memory consumption

G. Lu, V. Ly, C. Kambhamettu
{"title":"Large-scale Structure-from-Motion Reconstruction with small memory consumption","authors":"G. Lu, V. Ly, C. Kambhamettu","doi":"10.1145/2536853.2536897","DOIUrl":null,"url":null,"abstract":"Structure-from-Motion reconstruction is to recover the 3 dimensional structure from 2 dimensional images. Recent research in this field demonstrates the ability to reconstruct cities based on images extracted from a photo collection website; SIFT feature is typically extracted to detect correspondences between images. For the reconstruction of large scale unsorted images, the system is required to store all features and points information in the memory to search for correspondences. As SIFT feature is a 128 dimensional real-valued vector, storing each descriptor would consume a significant amount of memory. Due to this limitation, we propose to project the high-dimensional feature into a lower-dimensional space by using a new learned projection matrix while still maintaining the property of the original features. Hence, the result of this projection will shorten the distance among descriptors of the same point while lengthening the distance among descriptors of different points. These projected descriptors use Hellinger distance for calculation of the similarity between features. Furthermore, we learn a mapping function, which will map the real-valued descriptor into binary code coping with the variation of correspondence searching method. Experiments demonstrate that our method achieve excellent results with limited memory requirement.","PeriodicalId":135195,"journal":{"name":"Advances in Mobile Multimedia","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Mobile Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2536853.2536897","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Structure-from-Motion reconstruction is to recover the 3 dimensional structure from 2 dimensional images. Recent research in this field demonstrates the ability to reconstruct cities based on images extracted from a photo collection website; SIFT feature is typically extracted to detect correspondences between images. For the reconstruction of large scale unsorted images, the system is required to store all features and points information in the memory to search for correspondences. As SIFT feature is a 128 dimensional real-valued vector, storing each descriptor would consume a significant amount of memory. Due to this limitation, we propose to project the high-dimensional feature into a lower-dimensional space by using a new learned projection matrix while still maintaining the property of the original features. Hence, the result of this projection will shorten the distance among descriptors of the same point while lengthening the distance among descriptors of different points. These projected descriptors use Hellinger distance for calculation of the similarity between features. Furthermore, we learn a mapping function, which will map the real-valued descriptor into binary code coping with the variation of correspondence searching method. Experiments demonstrate that our method achieve excellent results with limited memory requirement.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
具有小内存消耗的大规模运动结构重构
从运动中恢复结构是一种从二维图像中恢复三维结构的方法。该领域的最新研究表明,基于从图片集网站提取的图像重建城市的能力;通常提取SIFT特征来检测图像之间的对应关系。对于大规模未排序图像的重建,要求系统将所有的特征和点信息存储在存储器中,以查找对应关系。由于SIFT特征是一个128维实值向量,因此存储每个描述符将消耗大量内存。由于这一限制,我们提出使用新的学习投影矩阵将高维特征投影到低维空间,同时仍保持原始特征的性质。因此,这种投影的结果将缩短同一点的描述子之间的距离,而延长不同点的描述子之间的距离。这些投影描述符使用海灵格距离来计算特征之间的相似性。此外,我们还学习了一个映射函数,该函数可以将实值描述符映射为二进制代码,以应对对应搜索方法的变化。实验表明,该方法在有限的内存要求下取得了很好的效果。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Contextual Geospatial Picture Understanding, Management and Visualization Measurement of Inter-Frequency Small Cell in Heterogeneous Networks Efficient Monitoring of Moving Mobile Device Range Queries using Dynamic Safe Regions Energy-Aware Adaptation of Educational Multimedia in Mobile Learning A System for Real-Time High-Level Geo-Information Extraction and Fusion for Geocoded Photos
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1