Anchor Segment Detection for Content Enhancement

Number: 20240289982
Published: 2024-08-29
Filed: 2024-01-31
Assignee: Disney Enterprises, Inc.
Inventors: Maggio; Nicholas et al.
CPC: G06T7/73; G06T11/00; G06T7/246; G06T7/269; G06T7/40
Verdict: Set aside content segmentation, business
Source: Google Patents · FreePatentsOnline

Abstract

A system includes a hardware processor and a system memory storing software code. The hardware processor is configured to execute the software code to receive reference content including a plurality of images in sequence, analyze the plurality of images to identify pixel feature changes between sequential images of the plurality of images, and identify, based on the pixel feature changes, one or more static image segments within the plurality of images. The hardware processor is further configured to execute the software code to evaluate the one or more static image segments using at least one of a size criterion or a visual feature criterion, select, based on evaluating, one of the one or more static image segments as an anchor segment, and provide mapping data identifying a location of the anchor segment within each of the plurality of images.

Background

BACKGROUND

Augmented reality (AR) applications seek to enhance content by overlaying virtual features on the content as it is rendered on a display screen. When implemented as intended, AR effects can advantageously provide users with a more immersive and enjoyable content consumption experience.

Despite their potential for increasing user enjoyment of content, challenges remain in identifying desirable image anchors for AR effects. Additionally, further complications can arise when accessibility feature overlays such as subtitles or captioning occlude elements of the image necessary for AR tracking (i.e., an image anchor). For example, locating such an image anchor for an AR effect in a portion of a video frame undergoing dynamic changes between video frames during an action sequence can significantly impair the ability of an AR application to detect and track the media content. Consequently, there is a need in the art for an automated solution enabling identification of static portions of images that can be used as image anchors for AR effects.

Claims

1. A system comprising: a hardware processor, and a system memory storing a software code; the hardware processor configured to execute the software code to: receive reference content including a plurality of images in sequence; analyze the plurality of images to identify pixel feature changes between sequential images of the plurality of images; identify, based on the pixel feature changes, one or more static image segments within the plurality of images; evaluate the one or more static image segments using at least one of a size criterion or a visual feature criterion; select, based on evaluating, a first image segment of the one or more static image segments as an anchor segment; and provide mapping data identifying a location of the anchor segment within each of the plurality of images. || 11. A method for use by a system including a hardware processor and a system memory storing a software code, the method comprising: receiving, by the software code executed by the hardware processor, reference content including a plurality of images in sequence; analyzing, by the software code executed by the hardware processor, the plurality of images to identify pixel feature changes between sequential images of the plurality of images; identifying, by the software code executed by the hardware processor based on the pixel feature changes, one or more static image segments within the plurality of images; evaluating, by the software code executed by the hardware processor, the one or more static image segments using at least one of a size criterion or a visual feature criterion; selecting, by the software code executed by the hardware processor based on evaluating, one of the one or more static image segments as an anchor segment; and providing, by the software code executed by the hardware processor, mapping data identifying a location of each of the anchor segment within each of the plurality of images.