A method for identifying a product which appears in a video stream. The method includes playing the video stream on a video playback device, identifying key scenes in the video stream containing product images, selecting product images identified by predetermined categories of trained neural-network object identifiers stored in training datasets. Object identifiers of identified product images are stored in a database. Edge detection and masking is then performed based on at least one of shape, color and perspective of the object identifiers. A polygon annotation of the object identifiers is created using the edge detection and masking. The polygon annotation is annotated to provide correct object identifier content, accuracy of polygon shape, title, description and URL of the object identifier for each identified product image corresponding to the stored object identifiers. Also disclosed is a method for an end user to select and interact with an identified product.

With respect to a video display apparatus, a technology capable of improving the operability and usability for a user in relation to a generated image such as AR (Augmented Reality) is provided. An HMD as a video display apparatus displays an AR image on a display screen, configures an ID image including identification information (ID) for supporting an operation of a user to the AR image, detects a sight line direction of the user to set a sight line region, and displays the ID image so as to be associated with the AR image when the AR image falls within a range of the sight line region. The HMD receives an operation to select the ID image from the user, selects the AR image associated with the ID image when receiving the operation to select the ID image, and executes a predetermined process associated with the AR image.

A method and a sports analytics system (SAS) for analyzing a live video broadcast stream (LVBS) of a sporting event are provided. The SAS splits the LVBS into a real time messaging protocol (RTMP) stream and a hypertext transfer protocol live stream (HLS) and analyses the RTMP stream using a phase difference between the RTMP stream and the HLS. The SAS detects persons present in a frame of the RTMP stream using a first set of cues and tracks the detected persons by analyzing preceding frames. The SAS recognizes the tracked persons using a second set of cues, assigns individual weights to each of the second set of cues, and compares the assigned weights of each of the recognized persons with pre-existing data of all players to identify the players in the frame. The SAS transmits the HLS and contextual interactive content of the identified players to a user device.

Systems and methods are provided for generating a trackable video-based product. One method comprises receiving a video comprising a plurality of frames from a video database; receiving product information associated with at least one product for sale from a product database; and receiving annotation data linking the received product information to at least one of the plurality of frames from a metadata database. The method may further comprise modifying a database to include a link between the at least one of the plurality of frames and the product information and generating an augmented video using the annotation data and the received video. The method may further comprise delivering the augmented video to a client device, such as a user device of a consumer, and responsive thereto receiving a communication related to the delivered video, the communication comprising data relating to an interaction with the video; comparing the data relating to the interaction with the link in the database to determine an associated product; and delivering information associated with the determined associated product to the client device.

A method for providing online shopping information based on video analysis is performed by one or more processors of a user terminal. The method includes while a video is playing, outputting a first tag associated with a first object included in the video, at a location adjacent to the first object, while the video is playing, outputting a second tag associated with a second object included in the video, at a location adjacent to the second object, while the video is playing, receiving a first user input of selecting the first tag, the first user input being a first input of a user of the user terminal, and in response to receiving the first user input, outputting information on a first product registered in an online shopping platform associated with the first object.

A method for providing online shopping information based on video analysis is performed by one or more processors of a user terminal. The method includes while a video is playing, outputting a first tag associated with a first object included in the video, at a location adjacent to the first object, while the video is playing, outputting a second tag associated with a second object included in the video, at a location adjacent to the second object, while the video is playing, receiving a first user input of selecting the first tag, the first user input being a first input of a user of the user terminal, and in response to receiving the first user input, outputting information on a first product registered in an online shopping platform associated with the first object.

Methods, systems, and apparatuses for predicting a user field-of-view change and determining transmission regions of immersive video (IV) content for an IV device are presented. A field-of-view change of a user device may be predicted. A transmission region in one or more video frames of the IV content may be determined based on the predicted change.

Methods, systems, and apparatuses for predicting a user field-of-view change and determining transmission regions of immersive video (IV) content for an IV device are presented. A field-of-view change of a user device may be predicted. A transmission region in one or more video frames of the IV content may be determined based on the predicted change.

The present invention relates to: a terminal capable of setting a trigger area and outputting additional contents in response to an input of touching the set trigger area; and a control method therefor. The terminal according to the present invention can comprise a touch screen for displaying information and receiving a touch input, and a control unit for performing control so as to output main contents on the touch screen, set a trigger area linked to a plurality of additional contents on the main content, output a list of the plurality of additional contents linked to the trigger area in response to a touch input of touching the trigger area when an edit mode for allowing setting of the trigger area is terminated and a viewer mode is executed, and output first additional contents corresponding to the selected item when any one is selected from the list.

An omnidirectional media playback method, a terminal device and a computer readable storage medium. The method comprises: obtaining viewpoint looping information associated to a current viewpoint from omnidirectional media data (S202); and looping the current viewpoint according to the viewpoint looping information (S204). A mechanism for allowing viewpoint looping is provided and information about the viewpoint looping is defined.