In order to improve a cropping system by obtaining the coverage of a wide range of contents for smaller sized displays of handheld devices, the invention proposes a method starting from a metadata aggregation and the corresponding video, e.g. in post-production, programme exchange and archiving, wherein (a) the video is passed through to a video analysis to deliver video, e.g. by use of motion detection, morphology filters, edge detection, etc., (b) the separated video and metadata are combined to extract important features in a context wherein important information from the metadata is categorised and is used to initialise a dynamically fitted chain of feature extraction steps adapted to the delivered video content, (c) extracted important features are combined to defione regions of interest (ROI) which are searched in consecutive video frames by object tracking, said object tracking identifies the new position and deformation of each initialised ROI in consecutive video frames and returns this information to the feature extraction thereby obtaining a permanent communication between said feature extraction and said object tracking, (d) one or several ROIs are extracted and inputted video frame by video frame into a cropping step (e); based on weighting information a well composed image part is cropped by classifying said supplied ROIs by importance, and (f) said cropped image area(s) are scaled to the desired small screen size.
A method of adapting video images to small screen sizes
European Patent N° WO2009115101 (A1)
PERMALINK : https://www.eurecom.fr/publication/3298