Interactive segmentation and tracking of video objects

Abstract

This paper describes a mechanism to interactively segment objects from a sequence of video frames. The extracted object can be later embedded in a different background, associated to local scale metadata or used to train an automatic object detector. The workflow requires the interaction of the user at two stages: the temporal segmentation of the frames containing the object and the generation of an object mask to initialize a video tracker. The mask is defined as a combination of regions generated by an image segmentation algorithm. This framework has been integrated in an annotation tool available to the public.