The FotoInMotion consortium launched its activities by performing an extensive analysis of the innovation tools and trends in the video and image processing marketplace along with features, pricing and platform analysis, enabling the team to reach to a common understanding of the currents status and, therefore, conclude to a joint vocabulary between end users and technical partners. That extensive analysis allowed the end users to develop a concrete and full set of user requirements, which were then “translated” into technical requirements by all technical partners.
Based on the user requirements and the project’s goals, and the components of the system and the interactions between them were defined, in order to constitute the overall architecture of the system. This architecture follows a distributed pattern where the communication between the components is done through a set of synchronous and asynchronous secured web services.
In parallel with the end users and based on user requirements, technical partners have initiated experimentation of state-of-the-art Machine Learning-based platforms and algorithms for the extraction and identification of visual features. Based on these results, the functional specifications of the visual analysis and classification component (iCAT) were defined and the relevant APIs for its integration within the complete FotoInMotion system architecture, were implemented
In parallel, the technical team selected and adopted a set of neural networks and started to configure, parametrise, train, and fine-tune them, to analyse photographs and identify features relevant for the FotoInMotion use cases. That lead to the development of the FotoInMotion image annotation tool (AAT). Such tool receives the output of the image analysis and features extraction tools and enables the user to enhance and/or augment the automatically obtained tags. In turn, it provides new training material and data to assess, validate, re-train and fine-tune the mentioned image analysis tools.
The technical partners have been also working towards developing and testing the 2D image editing quality assistance tools, used by end users to prepare images to be processed by the FotoInMotion application. This refers to actions like cropping, changing the color balances and apply transformations on images. The team has also developed and tested a set of video and audio effects, like pan, zoom, pitch etc to assist narration and, consequently, produce 2D videos in various video qualities and 3D videos.
All technical work has been capitalized into the development of the web and mobile applications, which were pilot tested by the end users. The web and mobile applications, through continuous iterations based on the user’s feedback were updated and new functionalities were implemented in every iteration, to address all the user needs and specifications. Through the two applications, a user can perform various actions like upload his photos and audios, view his media library, extract templates, apply image, audio and video filters, and eventually create his own story, by generating a 2D or 3D video, which can be stored and shared to social media, based on the selected settings.
