Layout Recognition for Dynamic Contents Retrieval in Digital Signage

We report our approach to bridge dynamic content transfer from publicly available digital signage to users’ private smart devices, such as glass-like wearables and smartphones. We aim to address issues concerning dynamic multimedia signage that has its contents divided into several sections. This type of signage has become increasingly popular due to optimal content exposures. In contrast to prior research, our approach excludes computer vision (CV) based object recognition, and instead took a novel approach to identify how contents are being laid-out in a digital signage. We incorporate CV techniques to recognize basic layout features such as corners and line segments, which are obtained from camera frame of user’s device. Consequently, the visual features are combined to generate content layout map, which will be compared to pre-learned layout map to aggregate corrected perspective. To grab a specific content, users are able to choose a section within the captured layout using the device’s interface, which in turn creates a request to contents server to send respective content info based on a timestamp and a unique section ID. We describe implementation details, report preliminary results, and conclude with discussion of our experiences in implementation as well as highlighting our future plans.