中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Leveraging local and global descriptors in parallel to search correspondences for visual localization

文献类型：期刊论文

作者Zhang, Pengju1,2; Zhang, Chaofan3; Liu, Bingxi1,2; Wu, Yihong1,2
刊名PATTERN RECOGNITION
出版日期2022-02-01
卷号122
ISSN号0031-3203
关键词Visual localization 6DoF pose Parallel search Learning based descriptor
DOI10.1016/j.patcog.2021.108344
通讯作者Zhang, Chaofan(zcfan@aiofm.ac.cn) ; Wu, Yihong(yhwu@nlpr.ia.ac.cn)
英文摘要Visual localization to compute 6DoF camera pose from a given image has wide applications. Both local and global descriptors are crucial for visual localization. Most of the existing visual localization methods adopt a two-stage strategy: image retrieval first is performed by global descriptors, and then 2D-3D correspondences are made by local descriptors from 2D query image points and its nearest neighbor candidates which are the 3D points visible by these retrieved images. The above two stages are serially performed in these methods. However, due to the fact that 3D points obtained from the retrieval feedback are only rely on global descriptors, these methods cannot fully take the advantages of both local and global descriptors. In this paper, we propose a novel parallel search framework, which fully leverages advantages of both local and global descriptors to get nearest neighbor candidates of a 2D query image point. Specifically, besides using deep learning based global descriptors, we also utilize local descriptors to construct random tree structures for obtaining nearest neighbor candidates of the 2D query image point. We propose a new probability model and a new deep learning based local descriptor when constructing the random trees. In addition, a weighted Hamming regularization term to keep discriminativeness after binarization is given in loss function for the proposed local descriptor. The loss function co-trains both real and binary local descriptors of which the results are integrated into the random trees. Experiments on challenging benchmarks show that the proposed localization method can significantly improve the robustness and accuracy compared with the ones which get nearest neighbor candidates of a query local feature just based on either local or global descriptors. (c) 2021 Elsevier Ltd. All rights reserved.
WOS关键词FEATURES
资助项目National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[62002359] ; Natural Science Foundation of Anhui Province of China[2108085QF277] ; Beijing Advanced Discipline Fund[115200S001]
WOS研究方向Computer Science ; Engineering
语种英语
出版者ELSEVIER SCI LTD
WOS记录号WOS:000704891800013
资助机构National Natural Science Foundation of China ; Natural Science Foundation of Anhui Province of China ; Beijing Advanced Discipline Fund
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/125547]  
专题中国科学院合肥物质科学研究院
通讯作者Zhang, Chaofan; Wu, Yihong
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Hefei Inst Phys Sci, Anhui Inst Opt & Fine Mech, Beijing 230031, Anhui, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Pengju,Zhang, Chaofan,Liu, Bingxi,et al. Leveraging local and global descriptors in parallel to search correspondences for visual localization[J]. PATTERN RECOGNITION,2022,122.
APA Zhang, Pengju,Zhang, Chaofan,Liu, Bingxi,&Wu, Yihong.(2022).Leveraging local and global descriptors in parallel to search correspondences for visual localization.PATTERN RECOGNITION,122.
MLA Zhang, Pengju,et al."Leveraging local and global descriptors in parallel to search correspondences for visual localization".PATTERN RECOGNITION 122(2022).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。