TY - GEN
T1 - View reconstruction from images by removing vehicles
AU - Chen, Li
AU - Jin, Lu
AU - Dai, Jing
AU - Xuan, Jianhua
PY - 2010
Y1 - 2010
N2 - Reconstructing views of real-world from satellite images, surveillance videos, or street view images is now a very popular problem, due to the broad usage of image data in Geographic Information Systems and Intelligent Transportation Systems. In this paper, we propose an approach that tries to replace the differences among images that are likely to be vehicles by the counterparts that are likely to be background. This method integrates the techniques for lane detection, vehicle detection, image subtraction and weighted voting, to regenerate the "vehicle-clean" images. The proposed approach can efficiently reveal the geographic background and preserve the privacy of vehicle owners. Experiments on surveillance images from TrafficLand.com and satellite view images have been conducted to demonstrate the effectiveness of the approach.
AB - Reconstructing views of real-world from satellite images, surveillance videos, or street view images is now a very popular problem, due to the broad usage of image data in Geographic Information Systems and Intelligent Transportation Systems. In this paper, we propose an approach that tries to replace the differences among images that are likely to be vehicles by the counterparts that are likely to be background. This method integrates the techniques for lane detection, vehicle detection, image subtraction and weighted voting, to regenerate the "vehicle-clean" images. The proposed approach can efficiently reveal the geographic background and preserve the privacy of vehicle owners. Experiments on surveillance images from TrafficLand.com and satellite view images have been conducted to demonstrate the effectiveness of the approach.
KW - Gabor wavelet filtering
KW - vehicle detection
KW - view reconstruction
UR - http://www.scopus.com/inward/record.url?scp=78650893057&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650893057&partnerID=8YFLogxK
U2 - 10.1145/1869890.1869896
DO - 10.1145/1869890.1869896
M3 - Conference contribution
AN - SCOPUS:78650893057
SN - 9781450304306
T3 - Proc. of the 1st ACM SIGSPATIAL Int. Workshop on Data Mining for Geoinformatics, DMG 2010, offered under the auspices of the 18th Int. Conference on Advances in Geographic Information Systems, ACMGIS
SP - 45
EP - 52
BT - Proc. of the 1st ACM SIGSPATIAL Int. Workshop on Data Mining for Geoinformatics, DMG 2010, offered under the auspices of the 18th Int. Conference on Advances in Geographic Information Systems, ACMGIS
T2 - 1st ACM SIGSPATIAL International Workshop on Data Mining for Geoinformatics, DMG 2010, offered under the auspices of the 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, GIS'10
Y2 - 2 November 2010 through 2 November 2010
ER -