Abstract | ||
---|---|---|
Matching street-level images to a database of airborne images is hard because of extreme viewpoint and illumination differences. Color/gradient distributions or local descriptors fail to match forcing us to rely on the structure of self-similarity of patterns on facades. We propose to capture this structure with a novel "scale-selective self-similarity" (S4) descriptor which is computed at each point on the facade at its inherent scale. To achieve this, we introduce a new method for scale selection which enables the extraction and segmentation of facades as well. Matching is done with a Bayesian classification of the street-view query S4 descriptors given all labeled descriptors in the bird's-eye-view database. We show experimental results on retrieval accuracy on a challenging set of publicly available imagery and compare with standard SIFT-based techniques. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33863-2_18 | european conference on computer vision |
Keywords | Field | DocType |
bayesian classification,inherent scale,available imagery,bird s-eye-view database,s4 descriptors,local descriptors,airborne image,ultra-wide baseline facade,scale-selective self-similarity,scale selection,challenging set | Line segment,Computer vision,Scale-invariant feature transform,Naive Bayes classifier,Pattern recognition,Segmentation,Computer science,Ground plane,Artificial intelligence,Scale selection,Facade | Conference |
Volume | ISSN | Citations |
7583 | 2191-6586 | 20 |
PageRank | References | Authors |
0.77 | 16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mayank Bansal | 1 | 122 | 9.03 |
Konstantinos Daniilidis | 2 | 3122 | 255.45 |
Harpreet Sawhney | 3 | 265 | 14.93 |