Global IP video traffic will account for 79% of all consumer Internet traffic by 2018. With video content increasingly consumed online instead of via broadcast TV, ad spends are migrating to the web. However, web video is still a passive medium which does not fully exploit all the potentials of digital web technologies. Interactive video aims at filling this gap by creating engaging user experiences such as clickable or shoppable videos or immersive storytelling. Interactive videos are typically produced as single, very customised projects by creative designers and software developers for a specific video identified by the client. This procedure is limiting the exploitation of interactive videos into the current online video market where thousands of videos are released every day both for advertisement or content broadcasting. With IntelliTag, users will be able to efficiently, automatically or semiautomatically, create a large number of interactive videos just by specifying a set of metadata without the need of any specific technical knowledge. Tags or “hotspots” in the form of graphical calls-to-action will be linked to the specific elements appearing in the video and their motion will be tracked to allow the viewer to interact with the actual moving element. The system will be provided with an intuitive Graphical User Interface (GUI) which will allow the user to specify the elements of the videos that need to be made interactive. The user will be able to create overlays to be associated to a specific metadata in order to display product information, behind the scenes videos, competitions and any other external content to be linked to the video. Through this process the video will be made “intelligent” and connected to the web around. The system will make use of the most advanced Computer Vision and Machine Learning algorithms to extract semantic information from visual and audio data and associate them with interactive content to be displayed in the video.

Although video, television and film have developed from an analogue format into a digital viewing experience, the medium itself remains largely incomprehensible to machines. Whilst there have been huge advances in the ability to produce, distribute, store and display digital video cheaply and effectively, there is almost no intelligent digital understanding about the visual analogue objects video contains. The moving image that this data represents can only be fully understood by humans and at present video content is searched for and categorised by information contained within a title or filename and an often illusive description. The traditional medium doesn't have the characteristics of other data-rich assets we find in today's modern digital environment. Adding a digital stamp or reference point to moving video objects creates a link between the visual, two-dimensional, analogue shape and the power of third party digital data. This project aims to develop a tool that allows content owners and producers to analyse and process video files, from production rushes to final composed edits, so that picture information can be stored, moving people and objects can be; identified and recognised, their movement recorded and a digital reference point added. This allows content to be indexed and searched for by picture, people and objects it contains.