TY - JOUR
T1 - Aerial image sequence geolocalization with road traffic as invariant feature
AU - Máttyus, Gellért
AU - Fraundorfer, Friedrich
PY - 2016/8/1
Y1 - 2016/8/1
N2 - The geolocalization of aerial images is important for extracting geospatial information (e.g. the position of buildings, streets, and cars) and for creating maps. The standard is to use an expensive aerial imaging system equipped with an accurate GPS and IMU and/or do laborious ground control point measurements. In this paper we present a novel method to recognize the geolocation of aerial images automatically without any GPS or IMU. We extract road segments in the image sequence by detecting and tracking cars. We search in a database created from a road network map for the best matches between the road database and the extracted road segments. Geometric hashing is used to retrieve a shortlist of matches. The matches in the shortlist are ranked by a verification process. The highest scoring match gives the location and orientation of the images. We show in the experiments that our method can correctly geolocalize the aerial images in various scenes: e.g. urban, suburban, and rural with motorway. Besides the current images only the road map is needed over the search area. We can search an area of 22,500 km2 containing 32,000 km of streets within minutes on a single cpu.
AB - The geolocalization of aerial images is important for extracting geospatial information (e.g. the position of buildings, streets, and cars) and for creating maps. The standard is to use an expensive aerial imaging system equipped with an accurate GPS and IMU and/or do laborious ground control point measurements. In this paper we present a novel method to recognize the geolocation of aerial images automatically without any GPS or IMU. We extract road segments in the image sequence by detecting and tracking cars. We search in a database created from a road network map for the best matches between the road database and the extracted road segments. Geometric hashing is used to retrieve a shortlist of matches. The matches in the shortlist are ranked by a verification process. The highest scoring match gives the location and orientation of the images. We show in the experiments that our method can correctly geolocalize the aerial images in various scenes: e.g. urban, suburban, and rural with motorway. Besides the current images only the road map is needed over the search area. We can search an area of 22,500 km2 containing 32,000 km of streets within minutes on a single cpu.
KW - Geolocalization
KW - Geometric hashing
KW - Georeferencing
KW - Geotagging
UR - http://www.scopus.com/inward/record.url?scp=84978539267&partnerID=8YFLogxK
U2 - 10.1016/j.imavis.2016.05.014
DO - 10.1016/j.imavis.2016.05.014
M3 - Article
AN - SCOPUS:84978539267
SN - 0262-8856
VL - 52
SP - 218
EP - 229
JO - Image and Vision Computing
JF - Image and Vision Computing
ER -