Image-based Ciphering of Video Streams and Object Recognition for Urban and Vehicular Surveillance Services
Abstract
Nowadays, urban and vehicular surveillance systems are col-
lecting large amounts of image data for feeding recognition systems e.g.
towards proposing localization or navigation services. In many cases,
these image data cannot directly be processed in situ by the acquisition
systems in reason of their low computational capabilities. The acquired
images are transferred to remote computing servers through various com-
puter networks, then analyzed in details towards object recognition. The
objective of this paper is twofold i) presenting image-based cyphering
methods that can eciently be applied for securing the image transfer
against consequences of image interceptions (e.g.; man-in-the-middle at-
tacks) ii) presenting generic image-based analysis techniques that can be
exploited for object recognition. Experimental results show end-to-end
image-based solutions for fostering developments of surveillance systems
and services in urban and vehicular environments.