One or more highlights of a video stream may be identified. The highlights may be segments of a video stream, such as a broadcast of a sporting event, that are of particular interest to one or more users. According to one method, at least a portion of the video stream may be stored. The portion of the video stream may be compared with templates of a template database to identify the one or more highlights. Each highlight may be a subset of the video stream that is deemed likely to match the one or more templates. The highlights, an identifier that identifies each of the highlights within the video stream, and/or metadata pertaining particularly to the one or more highlights may be stored to facilitate playback of the highlights for the users.

Described herein is a method and system for automated, context sensitive and non-intrusive insertion of consumer-adaptive content in video. It assesses ‘context’ in the video that a consumer is viewing through multiple modalities and metadata about the video. The method and system described herein analyzes relevance for a consumer based on multiple factors such as the profile information of the end-user, history of the content, social media and consumer interests and professional or educational background, through patterns from multiple sources. The system also implements local-context through search techniques for localizing sufficiently large, homogenous regions in the image that do not obfuscate protagonists or objects in focus but are viable candidate regions for insertion for the intended content. This makes relevant, curated content available to a user in the most effortless manner without hampering the viewing experience of the main video.

With rapidly evolving technologies and emerging tools, sports-related videos generated online are rapidly increasing. To automate the sports video editing/highlight generation process, a key task is to precisely recognize and locate events-of-interest in videos. Embodiments herein comprise a two-stage paradigm to detect categories of events and when these events happen in videos. In one or more embodiments, multiple action recognition models extract high-level semantic features, and a transformer-based temporal detection module locates target events. These novel approaches achieved state-of-the-art performance in both action spotting and replay grounding. While presented in the context of sports, it shall be noted that the systems and methods herein may be used for videos comprising other content and events.

A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Systems and methods are operable to present a sporting event on a display based on a determined level of viewer engagement and a determined team preference of the viewer. An exemplary embodiment presents a neutral viewpoint video content segment on the display during the first period of game play when the viewer has a neutral team preference, alternatively presents a first team alternative video content segment on the display during the first period of game play when the viewer has a preference for the first team, or alternatively presents a second team alternative video content segment on the display during the first period of game play when the viewer has a preference for the second team.

Techniques are disclosed to add augmented reality to a sub-view of a high resolution central video feed. In various embodiments, a central video feed is received from a first camera on a first recurring basis and time-stamped position information is received from a tracking system on a second recurring basis. The central video feed is calibrated against a spatial region encompassed by the central video feed. The received time-stamped position information and a determined plurality of tiles associated with at least one frame of the central video feed are used to define a first sub-view of the central video feed. The first sub-view and a homography defining placement of augmented reality elements on the at least one frame of the central video feed are provided as output to a device configured to use the first sub-view and the homography display the first sub-view.

An image processing apparatus generates, based on an input image, region information indicating a region including an object, determines, based on the region information, a region including an object to be transmitted, and transmits, based on the region information indicating the determined region, an image of the object and region information indicating the determined region.

According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.

A control apparatus that access first cameras capturing a first subject of a first area, and second cameras capturing a second subject of a second area, detects a viewing direction of a spectator group in the first subject on the basis of image data of the first subject captured by any one of first cameras, identifies a focus area in the second area that is focused on by the spectator group on the basis of the viewing direction of the spectator group, identifies a focus subject, focused on by the spectator group, that is present in the focus area on the basis of image data of the second subject captured by each of the second cameras, determines a specific second camera to be a transmission source of image data from among the second cameras on the basis of the focus subject, and transmits image data from the specific second camera.

The image processing apparatus obtains an image representing an object, performs specific processing for an object included in an area whose object extraction accuracy is lower than a threshold value in the captured image, and generates three-dimensional shape data of the object based on the image representing the object for which the specific processing has been performed.