Facilitating direct and ubiquitous mobile computer vision

Computer Vision (CV) approaches, e.g., as the basis for mobile Augmented Reality (AR), depend on continuous Internet access for image uploads and large-scale Internet databases to perform image recognition against comparison images. This dependency impedes the ubiquity of applying CV in spontaneous, real-world mobile scenarios as users may not have continuous Internet access. Furthermore, the underlying databases are inherently volatile and may only afford sporadic coverage. We hence propose DMCV (Direct Mobile Computer Vision), leveraging the proliferation of wireless communication capabilities in mobile and stationary devices to remove this dependency and to transmit CV image descriptors directly between mobile devices and recognizable objects. Building on 802.11 and Bluetooth, we explore the design space of local wireless CV information discovery and provision and evaluate to which degree each technology affords ubiquitous mobile CV. We show the feasibility and performance of our approach on commodity phones and evaluate the benefits provided by ubiquitous direct CV.