Abstract | ||
---|---|---|
Image matching is a fundamental problem in Computer Vision. In the context of feature-based matching, SIFT and its variants have long excelled in a wide array of applications. However, for ultra-wide baselines, as in the case of aerial images captured under large camera rotations, the appearance variation goes beyond the reach of SIFT and RANSAC. In this paper we propose a data-driven, deep learning-based approach that sidesteps local correspondence by framing the problem as a classification task. Furthermore, we demonstrate that local correspondences can still be useful. To do so we incorporate an attention mechanism to produce a set of probable matches, which allows us to further increase performance. We train our models on a dataset of urban aerial imagery consisting of 'same' and 'different' pairs, collected for this purpose, and characterize the problem via a human study with annotations from Amazon Mechanical Turk. We demonstrate that our models outperform the state-of-the-art on ultra-wide baseline matching and approach human accuracy. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CVPR.2016.385 | 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
Field | DocType | Volume |
Framing (construction),Scale-invariant feature transform,Computer vision,Human study,Pattern recognition,Image matching,RANSAC,Computer science,Artificial intelligence,Deep learning,Aerial imagery | Conference | 2016 |
Issue | ISSN | Citations |
1 | 1063-6919 | 6 |
PageRank | References | Authors |
0.42 | 20 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hani Altwaijry | 1 | 9 | 1.14 |
Eduard Trulls | 2 | 318 | 11.07 |
James Hays | 3 | 3942 | 172.72 |
Pascal Fua | 4 | 12768 | 731.45 |
Serge J. Belongie | 5 | 12512 | 1010.13 |