caa a22 4500 60544661X CHVBK 20210128100127.0 cr unu---uuuuu 210128e20151201xx s 000 0 eng 10.1007/s11042-014-2213-x doi (NATIONALLICENCE)springer-10.1007/s11042-014-2213-x Street sweeper: detecting and removing cars in street view images [Elektronische Daten] [Wei-Ta Chu, Ying-Chieh Chao, Yi-Sheng Chang] To protect privacy of individuals or companies that may be leaked in street view images, we present a system to automatically detect and remove cars as if they had never been there. Although street view service providers have made efforts on blurring human faces and license plates, we argue that remaining features, such as license numbers and phone numbers printed on car bodies, could cause privacy leak. Given a sequence of street view images, this system first detects cars by the deformable part model, and then determines foreground/background seeds for the GrabCut image segmentation module in order to facilitate automatic car segmentation. After removing cars, an exemplar-based inpainting method is developed with special designs on filling priority determination and road structure propagation. Hierarchical texture propagation and randomized texture propagation are integrated to implement the inpainting process, so that aesthetically pleasing inpainting results as well as privacy protection can be accomplished. Springer Science+Business Media New York, 2014 Cascade deformable part model nationallicence Grabcut nationallicence Road structure propagation nationallicence Hierarchical texture propagation nationallicence Randomized texture propagation nationallicence Chu Wei-Ta National Chung Cheng University, Taiwan, Republic of China aut Chao Ying-Chieh National Chung Cheng University, Taiwan, Republic of China aut Chang Yi-Sheng National Chung Cheng University, Taiwan, Republic of China aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/23(2015-12-01), 10965-10988 1380-7501 74:23<10965 2015 74 11042 https://doi.org/10.1007/s11042-014-2213-x text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-2213-x text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Chu Wei-Ta National Chung Cheng University, Taiwan, Republic of China aut NATIONALLICENCE 700 1- Chao Ying-Chieh National Chung Cheng University, Taiwan, Republic of China aut NATIONALLICENCE 700 1- Chang Yi-Sheng National Chung Cheng University, Taiwan, Republic of China aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/23(2015-12-01), 10965-10988 1380-7501 74:23<10965 2015 74 11042