![]() |
Department of
Computational
Perception
|
![]() |
SocialFilm
Project Title: SocialFilm
Sponsor: Austrian Research Promotion Agency (FFG),
Innovation Voucher
Industrial Partner: emotion3D
Duration: 5 months (July 2017 – November 2017)
Persons involved:
Abstract
Current smart phones and digital cameras allow users to create high-quality images easily without the need for professional expertise, e.g., in the field of photography. Based on fully automatic image analysis (for example, detection of closed eyes, automatic white balance, etc.), the device supports the user in taking pictues. In contrast, the creation of good short videos with the smart phone is still not easy to accomplish for the amateur users, since good camera movement puts significantly higher demands on them. To overcome this issue, emotion3D is working on a fully automated software tool to support users in the video production process on smart phones. This tool analyzes the quality of the video during recording, using intelligent image analysis (such as Optical Flow or Visual Odometry) and IMU sensors. It can identify and alert the user about aesthetic mistakes, e.g., poor camera direction or scene composition.