The present invention relates to a method for deriving a 3D data from image data comprising: receiving, from at least one camera, image data representing an environment; detecting, from the image data, at least one object within the environment; classifying the at least one detected object, wherein the method comprises, for each classified object of the classified at least one objects: determining a 2D skeleton of the classified object by implementing a neural network to identify features of the classified object in the image data corresponding to the classified object; and constructing a 3D skeleton for the classified object, comprising mapping the determined 2D skeleton to 3D.

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.

Techniques related to performing object or person association or correspondence in multi-view video are discussed. Such techniques include determining correspondences at a particular time instance based on separately optimizing correspondence sub-matrices for distance sub-matrices based on two-way minimum distance pairs between frame pairs, generating and fusing tracklets across time instances, and adjusting correspondence, after such tracklet processing, via elimination of outlier object positions and rearrangement of object correspondence.

Augmented reality systems provide graphics over views from a mobile device for both in-venue and remote viewing of a sporting or other event. A server system can provide a transformation between the coordinate system of a mobile device (smart phone, tablet computer, head mounted display) and a real world coordinate system. Requested graphics for the event are displayed over a view of an event.

Methods, systems, and computer-program products used for assessing athletic ability and generating performance data. In one embodiment, athlete performance data is generated through computer-vision analysis of video of an athletic performing, e.g., during practice or gameplay. The generated performance data for the athlete may include, for example, maximum speed, maximum acceleration, time to maximum speed, transition time (e.g., time to change direction), closing speed (e.g., time to close the distance to another athlete), average separation (e.g., between the athlete and another athlete), play-making ability, athleticism (e.g., a weighted computation and/or combination of multiple metrics), and/or other performance data. This performance data may be used to generate and/or update a profile associated with the athlete, which can be utilized for recruiting, scouting, comparing, and/or assessing athletes with greater efficiency and precision.

Methods and apparatus to generate photo-realistic three-dimensional models of a photographed environment are disclosed. An apparatus includes an object position calculator to determine a three-dimensional (3D) position of an object detected within a first image of an environment and within a second image of the environment. The apparatus further includes a 3D model generator to generate a 3D model of the environment based on the first image and the second image. The apparatus also includes a model integrity analyzer to detect a difference between the 3D position of the object and the 3D model. The 3D model generator automatically modifies the 3D model based on the difference in response to the difference satisfying a confidence threshold.

Systems and methods for constructing a grid model within video are disclosed. Exemplary implementations may: overlay one or more field line, hashmark line, or sideline on one or more frame of video; construct a plurality of evenly spaced longitudinal lines parallel to the one or more field line; detect, using a neural network model, one or more field object in the one or more fame of video; construct one or more anchor line along a top portion of a detected field object; construct a plurality of evenly spaced latitudinal lines parallel to the one or more hashmark line or the one or more anchor line; and overlay the plurality of evenly spaced longitudinal lines, the one or more anchor line, or the plurality of evenly spaced latitudinal lines on the one or more frame of video.

Methods, systems, graphical user interfaces (GUIs), and computer-readable media for presenting GUI elements generated based on information associated with an event are generally described. An event information presentation system may be configured to present GUI elements generated based on substantially real-time event information associated with a live event, such as a sporting event. Illustrative event information may include object movement and location information for objects such as event participants (for instance, players) and articles (for instance, a football for a football game event). The event information may be interpreted based on activity categories to automatically differentiate, organize, highlight, or the like the event information in order to generate relevant and meaningful GUI elements.

A method and apparatus for image processing, an electronic device, and a computer storage medium are provided. The method includes that: at least one frame of game platform image is acquired; the at least one frame of game platform image is detected to obtain a detection result of each of the at least one frame of game platform image, the detection result at least including position information of at least one money substitute; and under a condition that the position information of the at least one money substitute meets a preset alerting condition, first alert information is generated.

Disclosed herein are systems and method for determining environment dimensions based on environment pose. In one aspect, the method may include training, with a dataset including a plurality of images featuring an environment and labelled landmarks in the environment, a neural network to identify a pose of an environment. The method may comprise receiving an input image depicting the environment, generating an input tensor based on the input image, and inputting the input tensor into the neural network, which may be configured to generate an output tensor including a position of each identified landmark, a confidence level associated with each position, and a pose confidence score. The method may include calculating a homography matrix between each position in the output tensor along a camera plane and a corresponding position in an environment plane in order to output an image that visually connects each landmark along the environment plane.