Salient video stills: content and context preserved

Abstract

A new class of images called salient stills is demonstrated and a software development platform for their creation is discussed. These images do not represent one discrete moment of time, as do a photograph or single video frame. Rather, one image reflects the aggregate of the temporal changes that occur in a moving image sequence with the salient features preserved. By the application of an affine transformation and non-linear temporal processing, multiple frames of an image sequence, which may include variations in focal-length or field-of-view, are combined to create a single still image. The still image may have multi-resolution patches, a larger field-of-view, or higher overall resolution than any individual frame in the original image sequence. It may also contain selected salient objects from any one of the sequence of video frames. The still can be created automatically or with user intervention. A by-product of the salient still process is a structured representation of moving image data.