Abstract | ||
---|---|---|
We show how to use simple 2.5D maps of buildings and recent advances in image segmentation and machine learning to geo-localize an input image of an urban scene: We first extract the façades of the buildings and their edges from the image, and then look for the orientation and location that align a 3D rendering of the map with these segments. We discuss how to use a 3D tracking system to acquire the data required for training the segmentation method, the segmentation itself, and how we use the segmentations to evaluate the quality of the alignment. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/JURSE.2017.7924573 | 2017 Joint Urban Remote Sensing Event (JURSE) |
Keywords | Field | DocType |
semantic segmentation,urban environments,3D localization,image segmentation,machine learning,urban scene,3D rendering,3D tracking system | Computer vision,Scale-space segmentation,3D rendering,Computer science,3d localization,Image texture,Segmentation,Segmentation-based object categorization,Image segmentation,Artificial intelligence,3d tracking | Conference |
ISSN | ISBN | Citations |
2334-0932 | 978-1-5090-5809-9 | 1 |
PageRank | References | Authors |
0.37 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anil Armagan | 1 | 1 | 0.37 |
Martin Hirzer | 2 | 592 | 18.74 |
Vincent Lepetit | 3 | 6178 | 306.48 |