Disney Enterprises, Inc.

Ximin Gong

Nikhil Deshpande

Gregory House

James W Appleby, Ii

Randy W Sills, Sr

Cen Rao

Peter A Von Kaenel

Yuecheng Zhang

Ilke Levent Akin

Sheldon Katz

Eyal Shamur

One embodiment provides a method for rendering a virtual mark on a video frame, including: receiving the video frame, captured by a camera, comprising a scene; obtaining a three-dimensional model of a mark in the scene; obtaining a foreground mask of the video frame; denoting a predetermined region corresponding to a mark mask, wherein the mark mask is an image projection of the mark on the video frame; updating the mark mask to exclude foreground regions, wherein the updating comprises: partitioning the predetermined region into a plurality of segments; and filtering out, from the mark mask, foreground pixels based on the plurality of segments and the foreground mask; and rendering, on the video frame, the virtual mark using the updated mark mask. Other aspects are described and claimed.

Rendering a virtual mark on a video frame

A system and method for delaying a first version of a video feed from a video camera according to a first delay to generate a second version of the feed, supplying the first version to an insertion system, wherein the insertion system inserts an indicia into the first version to create an enhanced version with a second delay substantially matching the first delay and supplying the enhanced version and the second version to a production switcher, wherein the enhanced version and the second version supplied to the production switcher are synchronized with one another.

Multiple-input configuration and playback video enhancement

An apparatus and method for receiving a current video frame of a program video having a plurality of scene cuts switching between video segments originating from respective cameras of a plurality of cameras and automatically identifying the camera from which the current video frame originated. The apparatus having a feature database storing predetermined features for a plurality of cameras filming a program video originating from the plurality of cameras, a recognition unit receiving a current video frame of the program video, extracting features from the current video frame, and comparing the features to the previously stored features and a camera model estimator computing an estimated camera model based on corresponding feature pairs and previously stored features, wherein if the estimated camera model is within a predetermined threshold of a stored camera model for one of the plurality of cameras, that camera is identified as originating the current video frame.

Automatic camera identification from a multi-camera video stream

A method, apparatus, and computer program product are described that utilizes spatial modeling to represent foreground objects of an event to allow virtual graphics to be integrated into a background of the event in the presence of dynamic objects. The present invention detects a presence of dynamic objects within a region of interest from a video depicting the event. The present invention produces a suppression key corresponding to the dynamic object when present in the video or a suppression key with a default value when and where no dynamic object is present in the video.

Key generation through spatial detection of dynamic objects

A method of adding a virtual insertion to an image, according to an embodiment, includes extracting dynamic features from an input image, associating the dynamic extracted features with dynamic reference features in a reference feature database, generating a camera model based on the associations, mixing a virtual insertion into the input image based on the camera model, and outputting an image containing both the input image and the virtual insertion. According to another embodiment, a method of adding a virtual insertion to an image includes generating a biased camera model using a statistically selected subset of a plurality of non-fixed regions of the image, locating fixed reference objects in the image using the biased camera model as an entry point for a search, generating a corrected camera model using the fixed reference objects in the image, and adding a virtual insertion to the image using the corrected camera model.

Growing community of inventors

Belle Mead, NJ, United States of America

Ximin Gong