AnnoTone

Abstract

We present a video annotation system called "AnnoTone", which can embed various contextual information describing a scene, such as geographical location. Then the system allows the user to edit the video using this contextual information, enabling one to, for example, overlay with map or graphical annotations. AnnoTone converts annotation data into high-frequency audio signals (which are inaudible to the human ear), and then transmits them from a smartphone speaker placed near a video camera. This scheme makes it possible to add annotations using standard video cameras with no requirements for specific equipment other than a smartphone. We designed the audio watermarking protocol using dual-tone multi-frequency signaling, and developed a general-purpose annotation framework including an annotation generator and extractor. We conducted a series of performance tests to understand the reliability and the quality of the watermarking method. We then created several examples of video-editing applications using annotations to demonstrate the usefulness of Annotone, including an After Effects plugin.

A data hiding approach for sensitive smartphone data

“…Zhou et al [40] developed a system named AppInk that generates watermarked apps from the source code of original apps, to detect unauthorised apps which are repackaged by attackers. Suzuki et al [35] developed a video annotation system which embeds real-time highfrequency audio watermarks into video data of a smartphone camera. Because high-frequency audio is inaudible to humans, the audio quality of watermarked video data is not compromised.…”

“…Much like sensor nodes operating in an untrusted network [38,39], we can enable users' personal devices to share sensor data with each other via untrusted platforms. Additionally, our approach establishes a physical binding between a sensor stream and annotation data, either to prove ownership of the sensor data (as demonstrated with photos [27]), to provide additional context (as has been shown for videos [35]), or for ad-hoc communication purposes (as has been used in ad-hoc pairing [26,30]). …”

Automatic Live Sport Video Streams Curation System from User Generated Media

“…In this paper, the image feature data is manually assigned by human. However, it can be assigned automatically by using a special camera (Suzuki, et al, 2015), a special wearable device (Plötz, et al, 2012), or using existing annotation techniques (Yonezawa, et al, 2014;Sarvas, et al, 2004;Xu, et al, 2008). The proposed system will support the above automatic image feature data assignment in the future.…”