Intel Corporation

Stats LLC

Yuri Shpalensky

Maria Bortman

Tzach Ashkenazi

Roland Mishaev

Wenlong Li

Gal Oz

Danielle Shor

Alex Gendelman

Asaf Shiloni

Roy Tenny

Michael Birenboim

Techniques related to generating a fine super resolution image from a low resolution image including a person wearing a predetermined uniform are discussed. Such techniques include applying a pretrained convolutional neural network to a stacked image including image channels from a coarse super resolution image, label data corresponding to the coarse super resolution image from available labels relevant to the uniform, and pose data corresponding to the person to determine the fine super resolution image.

Method and apparatus for person super resolution from low resolution image

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.

Methods and apparatus to generate photo-realistic three-dimensional models of a photographed environment

It is provided a method for conveying data on a flying object in a scene. The method including capturing video frames of the scene by video cameras to get video frames which include image of the object, identifying the object in captured video frames to get associated object parameters, calculating motion variables, solving motion equations for anticipated object trajectory taking into account certain effects, and conveying data to displaying devices. The certain effects are an effect of object collision with a ground surface, air friction, wind effect, and interaction of a spinning object with air. The method may be applied to a ball in a sporting playing field. The cameras may have variable operating parameters desirable for the calculating the motion variables, which may be determined by camera calibration using captured artifacts of the scene. Shadow of the object may be captured as well and be used to provide data absent due to occluding a of the object from a video camera. Also, the captured frames of a ball may be used to calculate parameters relating to a bat which hits the ball.

Trajectory detection and analysis in sporting events

Growing community of inventors

Givataim, Israel

Yuri Shpalensky