Title :
Geolocalization using skylines from omni-images
Author :
Ramalingam, Srikumar ; Bouaziz, Sofien ; Sturm, Peter ; Brand, Matthew
Author_Institution :
Mitsubishi Electr. Res. Lab. (MERL), Cambridge, MA, USA
fDate :
Sept. 27 2009-Oct. 4 2009
Abstract :
We propose a novel method to accurately estimate the global position of a moving car using an omnidirectional camera and untextured 3D city models. The camera is oriented upwards to capture images of the immediate skyline, which is generally unique and serves as a fingerprint for a specific location in a city. Our goal is to estimate global position by matching skylines extracted from omni-directional images to skyline segments from coarse 3D city models. Our contributions include a sky segmentation algorithm for omni-directional images using graph cuts and a novel approach for matching omni-image skylines to 3D models.
Keywords :
cameras; feature extraction; geographic information systems; graph theory; image matching; image sensors; image texture; geolocalization; graph cuts; immediate skyline; matching skyline extraction; omni-images; omnidirectional camera; untextured 3D city models; Calibration; Cameras; Cities and towns; Computer vision; Conferences; Fingerprint recognition; Image segmentation; Layout; Optical distortion; Robustness;
Conference_Titel :
Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-4442-7
Electronic_ISBN :
978-1-4244-4441-0
DOI :
10.1109/ICCVW.2009.5457723
