Responding to a request from a potential customer, DataArt’s R&D department created a prototype application for object recognition and tracking within a video.
The customer’s idea for the product was that an object, selected manually in a video for the first time, is then tracked automatically throughout the footage, with the object coordinates retrieved and stored as the video progresses.
DataArt’s computer vision scientists and engineers timely conducted a feasibility study, which appeared to be positive, and created a prototype object tracking application.
The application allows loading a video, pointing at an object at a specific frame (or again later if the automatic tracking fails), and runs an object tracking analysis over the loaded file. The object is located in the following frames, and the location of the object is stored along with the video as a key-value file, where the calculated coordinates of the object correspond to the current playback time.
A commercial playback application could, using this information, then place an ad over the video at these specific coordinates during the playback, thus allowing for dynamic context advertising.