Disney Enterprises, Inc.

Yuecheng Zhang

Gregory House

Smadar Gefen

Ilke Levent Akin

Nikhil Deshpande

Ximin Gong

Cen Rao

Systems and methods for analyzing scenes from cameras imaging an event, such as a sporting event broadcast, are provided. Systems and methods include detecting and tracking patterns and trails. This may be performed with intra-frame processing and without knowledge of camera parameters. A system for analyzing a scene may include an object characterizer, a foreground detector, an object tracker, a trail updater, and a video annotator. Systems and methods may provide information regarding centers and spans of activity based on object locations and trails, which may be used to control camera field of views such as a camera pose and zoom level. A magnification may be determined for images in a video sequence based on the size of an object in the images. Measurements may be determined from object trails in a video sequence based on an effective magnification of images in the video sequence.

Objects trail-based analysis and control of video

Described herein are apparatus, systems and methods for shadow assisted object recognition and tracking. The methods performed by the apparatus and system include identifying a blob within a video image, the video image having at least one object and at least one shadow of the at least one object, the at least one shadow of the at least one object cast by at least one light source. Identifying the blob includes identifying an object projection corresponding to the at least one object and a shadow projection corresponding to the at least one shadow. A location of an object portion of the at least one object is determined based on the shadow projection.

Apparatus, systems and methods for shadow assisted object recognition and tracking

Object trail-based analysis and control of video

A method including receiving a broadcast of an event comprising a plurality of frames; receiving, from a plurality of users, a corresponding plurality of inputs, each of the inputs relating to a characteristic of an object depicted in one of the frames of the broadcast; and analyzing the plurality of inputs to determine a best guess of the characteristic of the object in the frame.

Method and system for data collection using large-scale interactive user response

Described herein are methods and systems for video event detection for contextual annotation and synchronization. Exemplary embodiments relate to a method comprising receiving a video stream, extracting a first event from the video stream, determining an index value identifying a location within the video stream corresponding to the first event, and inserting content based on the first event at a location identified by the index value. Further exemplary embodiments relate to a system comprising an event-based data extractor that receives a video stream and extracts a first event from the video stream, a processor that determines an index value identifying a location within the video stream corresponding to the first event, and a video insertion module inserts content based on the first event at a location identified by the index value.

Method and system for video event detection for contextual annotation and synchronization

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

Systems and methods for tracking the foreground and background objects in a video image sequence. The systems and methods providing for determining a camera model based on a first group of feature points extracted from a video frame, extracting three-dimensional (3D) information for the first group of feature points based on the camera model and a previous camera model for a previous video frame, reassigning feature points to the first group or a second group, based on mapping each feature point to a corresponding 3D model using the extracted 3D information for each feature point and determining a new camera model when a number of reassigned feature points is greater than a predetermined threshold.

Growing community of inventors

Princeton, NJ, United States of America

Yuecheng Zhang