AUTOMATIC COMPOSITION OF COMPOSITE IMAGES OR VIDEOS FROM FRAMES CAPTURED WITH MOVING CAMERA

摘要

A processing device generates composite images from a sequence of images. The composite images may be used as frames of video. A foreground/background segmentation is performed at selected frames to extract a plurality of foreground object images depicting a foreground object at different locations as it moves across a scene. The foreground object images are stored to a foreground object list. The foreground object images in the foreground object list are overlaid onto subsequent video frames that follow the respective frames from which they were extracted, thereby generating a composite video.

主权项

1. A method for generating a composite output image from an input video having a sequence of frames, the method comprising:
receiving a sequence of image frames depicting a foreground object, the sequence of image frames captured by a camera experiencing motion; for selected frames in the sequence of image frames, performing by a processing device, foreground/background segmentations to extract respective foreground object images each comprising a representation of the foreground object with background pixels subtracted and storing the respective foreground object images to a foreground object list; determining for each of the respective foreground object images in the foreground object list, a respective motion the camera between the camera capturing the selected frame corresponding to the respective foreground object image and the camera capturing a current frame; transforming the representations of the foreground objects in the foreground object images based on the respective motions to generate transformed foreground object images; and overlaying the transformed foreground object images onto the current frame to generate a composite output image.