There is provided a system and method for automated video segmentation of an input video signal. The input video signal capturing a playing surface of a team sporting event. The method including: receiving the input video signal; determining player position masks from the input video signal; determining optic flow maps from the input video signal; determining visual cues using the optic flow maps and the player position masks; classifying temporal portions of the input video signal for game state using a trained hidden Markov model, the game state comprising either game in play or game not in play, the hidden Markov model receiving the visual cues as input features, the hidden Markov model trained using training data comprising a plurality of visual cues for previously recorded video signals each with labelled play states; and outputting the classified temporal portions.

The present technology relates to an information processing apparatus, an information processing method, and a program capable of easily setting a frame for starting predetermined processing in a moving image of a play in a ball game.

The information processing apparatus includes: an analysis unit that detects a trajectory of a ball in a first moving image; and a start frame setting unit that sets a start frame for starting predetermined processing among frames of the first moving image on the basis of a detection result of the trajectory of the ball in the first moving image. The present technology can be applied to, for example, a system that analyzes a rotation characteristic of a serve in table tennis.

Disclosed herein are systems and method for classifying objects in an image using a color-based neural network. A method may include: training a neural network to classify an object in a given image into a color class from a set of color classes; determining, from the set of color classes, a subset of color classes that are anticipated to be in a received input image based on image metadata; generating a matched mask input indicating the subset; inputting both the input image and the matched mask input into the neural network, wherein the neural network is configured to: determine a first semantic embedding of the input image and the matched mask input; outputting a color class associated with a second semantic embedding with a least amount of distance to the first semantic embedding from a plurality of semantic embeddings.

A computer-implemented system and method of configuring a path of a virtual camera. The method comprises receiving user steering information to control the path of the virtual camera in a scene; determining a primary target based upon a field of view of the virtual camera; and estimating a future path and a corresponding future field of view of the virtual camera, based on the received steering information. The method further comprises determining a secondary target of the scene proximate to the estimated future path of the virtual camera based on a preferred perspective of the secondary target; and configuring the path to capture the secondary target from the preferred perspective.

Systems and methods for enhanced training of machine learning systems based on automatically generated visually realistic gameplay. An example method includes obtaining electronic game data that includes rendered images and associated annotation information, the annotation information identifying features included in the rendered images to be learned, and the electronic game data being generated by a video game associated with a particular sport. Machine learning models are trained based on the obtained electronic game data, with training including causing the machine learning models to output annotation information based on associated input of a rendered image. Real-world gameplay data is obtained, with the real-world gameplay data being images of real-world gameplay of the particular sport. The obtained real-world gameplay data is analyzed based on the trained machine learning models. Analyzing includes extracting features from the real-world gameplay data using the machine learning models.

A system for monitoring and recording and processing an activity includes one or more cameras for automatically recording video of the activity. A remote media system is located at the location of the activity. A network media processor and services is communicatively coupled with the remote media system. The remote media system includes one or more AI enabled cameras. The AI enabled camera is configured to record the activity. The network media processor is configured to receive an activation request of the AI enabled camera and validate the record request.

The present invention provides a user with a user interface for enabling the user to efficiently perform an operation for generating a virtual viewpoint image for each imaging target subject to be imaged by a plurality of imaging apparatuses. An event information acquisition unit acquires information about an event subjected to virtual viewpoint image generation, and transmits the acquired event information to a user interface (UI) determination unit. The UI determination unit determines a UI to be generated by a UI generation unit based on the event information transmitted from the event information acquisition unit. The UI generation unit generates the UI determined by the UI determination unit. The user performs an input operation for generating a virtual viewpoint image according to the UI generated by the UI generation unit.

A non-transitory recording medium storing an information processing program executable by a computer to perform processing, the processing comprising: acquiring a sound signal collected by a microphone provided in a venue including a skating rink, and a video obtained by imaging a competitor competing at the skating rink; estimating a takeoff-from-ice time and a landing-on-ice time of a jump performed by the competitor according to silencing and return of an ice sound based on the sound signal; and synchronizing time information of the sound signal with time information of the video and specifying, as a jump section, a section from a frame corresponding to the takeoff-from-ice time to a frame corresponding to the landing-on-ice time in the video.

Disclosed herein is a system and method directed to object tracking and metric generation using a plurality of cameras. The system includes the plurality of cameras disposed around a playing surface in a mirrored configuration, where the plurality of cameras are time-synchronized. The system further includes logic that, when executed by a processor, causes performance of operations including: obtaining a sequence of images from the plurality of cameras, continuously detecting an object in image pairs at successive points in time, wherein each image pair corresponds to a single point in time, continuously determining a location of the object within the playing space through triangulation of the object within each image pair, detecting a player and the object within each image of a subset of image pairs of the sequence of images, identifying a sequence of interactions between the object and the player, and storing the sequence of interactions.

Disclosed herein are systems and method for dynamically controlling a user interface for fantasy sports team management. In one aspect, a method may include receiving player statistics for a fantasy sports team generated by a user. The method may include calculating a team score for the fantasy sports team, wherein the calculated team score is a function of player statistics associated with the players with an active status, and wherein player statistics associated with the players with an inactive status do not influence the team score. The method may include generating, on a user interface, an option to change a status of at least one player with the inactive status into the active status during the fantasy sports match, and changing, in real-time, the status of the at least one player into the active status when the option is selected. The method may include determining an updated team score.