期刊
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
卷 -, 期 -, 页码 2391-2400出版社
IEEE
DOI: 10.1109/ICCV.2017.260
关键词
-
资金
- China Scholarship Council [201506290131]
- ARC [DP120103896, LP100100588, CE140100016, DE140100180]
- Australia ARC Centre of Excellence Program on Robotic Vision, NICTA (Data61)
- Natural Science Foundation of China [61420106007, 61473230, 61374023]
- State Key Laboratory of Geo-information Engineering [SKLGIE2015-M-3-4]
- Aviation Fund of China [2014ZC53030]
- NVIDIA Corporation
Given an image of a street scene in a city, this paper develops a new method that can quickly and precisely pinpoint at which location (as well as viewing direction) the image was taken, against a pre-stored large-scale 3D point-cloud map of the city. We adopt the recently developed 2D-3D direct feature matching framework for this task [23,31,32,42-44]. This is a challenging task especially for large-scale problems. As the map size grows bigger, many 3D points in the wider geographical area can be visually very similar-or even identical-causing severe ambiguities in 2D-3D feature matching. The key is to quickly and unambiguously find the correct matches between a query image and the large 3D map. Existing methods solve this problem mainly via comparing individual features' visual similarities in a local and per feature manner, thus only local solutions can be found, inadequate for large-scale applications. In this paper, we introduce a global method which harnesses global contextual information exhibited both within the query image and among all the 3D points in the map. This is achieved by a novel global ranking algorithm, applied to a Markov network built upon the 3D map, which takes account of not only visual similarities between individual 2D-3D matches, but also their global compatibilities (as measured by co-visibility) among all matching pairs found in the scene. Tests on standard benchmark datasets show that our method achieved both higher precision and comparable recall, compared with the state-of-the-art.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据