Abstract: A multi-camera architecture for detecting and tracking a ball in real-time. The multi-camera architecture includes network interface circuitry to receive a plurality of real-time videos taken from a plurality of high-resolution cameras. Each of the high-resolution cameras simultaneously captures a sports event, wherein each of the plurality of high-resolution cameras includes a viewpoint that covers an entire playing field where the sports event is played. The multi-camera architecture further includes one or more processors coupled to the network interface circuitry and one or more memory devices coupled to the one or more processors.

Abstract: Methods, systems and apparatuses may provide for technology that automatically determines, based on camera calibration data and trajectory data associated with a projectile in a game, a plurality of camera angles. The technology may also automatically generate, based on the plurality of camera angles, a camera path for a volumetric content replay of a three-dimensional (3D) region of interest around a highlight moment in the game.

Abstract: Methods, systems and apparatuses may provide for technology that identifies a player captured in a multi-camera video feed of a game that involves the identified player and estimates a first field of view from the perspective of the identified player for a selected from of the multi-camera video feed. Additionally, the technology automatically generates, based on the first field of view, a camera path for a replay of the selected frame from the perspective of the identified player. In one example, the technology also determines a trajectory of a projectile captured in the multi-camera video feed, estimates, based on the trajectory, a second field of view from the perspective of the projectile, and automatically generates, based on the second field of view, a replay of one or more selected frames of the multi-camera video feed from the perspective of the projectile.

Abstract: The disclosure discloses a method for extracting a boundary of a thin-walled part with small curvature based on three-dimensional point cloud. The method includes: collecting point cloud data of a part to reduce density of the point cloud data, performing Euclidean cluster to divide into point cloud pieces, obtaining triangular mesh surfaces for each point cloud triangulation; extracting a boundary vertex of each triangular mesh surface to obtain a contour thereof, selecting a contour of the part among all contours; searching with each point on the contour as a center to form a three-dimensional boundary point cloud band; projecting the three-dimensional boundary point cloud band to a plane, orderly extracting two-dimensional boundary points within the plane, and arranging corresponding points in the three-dimensional boundary point cloud band according to an order of ordered boundary points within the plane to obtain ordered boundary points in the three-dimensional boundary point cloud band.

Abstract: A mechanism is described for facilitating real-time multi-view detection of objects in multi-camera environments, according to one embodiment. A method of embodiments, as described herein, includes mapping first lines associated with objects to a ground plane; and forming clusters of second lines corresponding to the first lines such that an intersection point in a cluster represents a position of an object on the ground plane.

Abstract: Methods and apparatus to detect collision of a virtual camera with objects in a three-dimensional volumetric model are disclosed herein. An example virtual camera system disclosed herein includes cameras to obtain images of a scene in an environment. The example virtual camera system also includes a virtual camera generator to create a 3D volumetric model of the scene based on the images, identify a 3D location of a virtual camera to be disposed in the 3D volumetric model, and detect whether a collision occurs between the virtual camera and one or more objects in the 3D volumetric model.

Abstract: 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.

Abstract: Method, systems and apparatuses may provide for technology that extracts one or more motion features from filtered position data associated with a projectile in a game and identifies a turning point in a trajectory of the projectile based on the one or more motion features. The technology may also automatically designate the turning point as a highlight moment if one or more of the turning point or the trajectory satisfies a proximity condition with respect to a target area in the game.

Abstract: The present disclosure provides an apparatus and method for evaluate the quality of a three dimensional (3D) point cloud. The apparatus comprises an image segmenter to generate a segmented two-dimensional (2D) image for each of the plurality of images; a 2D mask generator to generate a 2D mask for each of the plurality of images from the 3D point cloud; a comparator to compare the segmented 2D image with the 2D mask to obtain a comparison result for each image; and an evaluator to evaluate the quality of the 3D point cloud based on aggregated comparison results for the plurality of images.

Abstract: The disclosure discloses a method for constructing actual processing curve of part with small curvature based on a point cloud boundary. The method includes: (a) encrypting a three-dimensional ordered boundary curve of a part to be processed; (b) fitting encrypted boundary points into a plane, and projecting each boundary point into the plane to obtain a projection point; (c) performing Euclidean cluster within the plane to obtain point sets, and fitting the obtained point sets into a straight line; (d) performing the Euclidean cluster on projection points that are not fitted into the straight line to obtain corner point sets, and fitting a sharp corner or a rounded corner of the corner point sets to obtain a fitted boundary curve within the plane; (e) mapping the fitted boundary curve to a curved surface of the three-dimensional ordered boundary curve to obtain an actual processing curve of the part to be processed.

Abstract: The disclosure discloses a method for extracting a boundary of a thin-walled part with small curvature based on three-dimensional point cloud. The method includes: collecting point cloud data of a part to reduce density of the point cloud data, performing Euclidean cluster to divide into point cloud pieces, obtaining triangular mesh surfaces for each point cloud triangulation; extracting a boundary vertex of each triangular mesh surface to obtain a contour thereof, selecting a contour of the part among all contours; searching with each point on the contour as a center to form a three-dimensional boundary point cloud band; projecting the three-dimensional boundary point cloud band to a plane, orderly extracting two-dimensional boundary points within the plane, and arranging corresponding points in the three-dimensional boundary point cloud band according to an order of ordered boundary points within the plane to obtain ordered boundary points in the three-dimensional boundary point cloud band.

Abstract: Smart apparel for monitoring athletics and associated systems and methods are disclosed. An example apparatus includes a data interface to access first motion data and second motion data generated by the smart apparel, the first motion data associated with a first joint on a body and the second motion data associated with a second joint on the body; a motion data fuser to fuse the first motion data and the second motion data; an analytics determiner to process the fused first and second motion data to identify a progression of a motion based activity; and a display organizer to generate a graphical display representing the progression of the motion based activity.

Abstract: A video capture and processing system includes a memory configured to store a pose database. The pose database includes poses that indicate a start or stoppage in an event. The system also includes a processor operatively coupled to the memory. The processor is configured to generate a pose of an individual in a video frame of captured video of the event. The pose can be three-dimensional pose or a two-dimensional pose. The processor is also configured to determine, based on the pose database, whether the pose of the individual indicates a start or a stoppage in the event. The processor is further configured to control an upload of video of the event based on the determination of whether the pose indicates the start or the stoppage in the event.

Abstract: Generally this disclosure describes a video communication system that replaces actual live images of the participating users with animated avatars. A method may include selecting an avatar; initiating communication; detecting a user input; identifying the user input; identifying an animation command based on the user input; generating avatar parameters; and transmitting at least one of the animation command and the avatar parameters.

Abstract: The invention belongs to a related field of electronic manufacturing technology, and particularly relates to a conformal manufacturing device and a method for a complex curved-surface electronic system, the system includes a support platform and a six-degree-of-freedom spherical motor linkage platform, a 3D measurement module, a laser lift-off module, a curved-surface transfer printing module and a conformal jet printing module respectively mounted on the support platform and independently controllable, and specific structures and work modes of these key components are improved. The invention further discloses a corresponding manufacturing method.

Abstract: System and techniques for positional analysis using computer vision sensor synchronization are described herein. A set of sensor data may be obtained for a participant of an activity. A video stream may be captured in response to detection of a start of the activity in the set of sensor data. The video stream may include images of the participant engaging in the activity. A key stage of the activity may be identified by evaluation of the sensor data. A key frame may be selected from the video stream using a timestamp of the sensor data used to identify the key stage of the activity. A skeletal map may be generated for the participant in the key frame using key points of the participant extracted from the key frame. Instructional data may be selected using the skeletal map. The instructional data may be displayed on a display device.

Abstract: Video analysis may be used to determine who is watching television and their level of interest in the current programming Lists of favorite programs may be derived for each of a plurality of viewers of programming on the same television receiver.

Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.

Abstract: An example apparatus is disclosed herein that includes a memory and at least one processor. The at least one processor is to execute instructions to: select a gesture from a database, the gesture including a sequence of poses; translate the selected gesture into an animated avatar performing the selected gesture for display at a display device; display a prompt for the user to perform the selected gesture performed by the animated avatar; capture an image of the user performing the selected gesture; and perform a comparison between a gesture performed by the user in the captured image and the selected gesture to determine whether there is a match between the gesture performed by the user and the selected gesture.

Abstract: System and techniques for positional analysis using computer vision sensor synchronization are described herein. A set of sensor data may be obtained for a participant of an activity. A video stream may be captured in response to detection of a start of the activity in the set of sensor data. The video stream may include images of the participant engaging in the activity. A key stage of the activity may be identified by evaluation of the sensor data. A key frame may be selected from the video stream using a timestamp of the sensor data used to identify the key stage of the activity. A skeletal map may be generated for the participant in the key frame using key points of the participant extracted from the key frame. Instructional data may be selected using the skeletal map. The instructional data may be displayed on a display device.