| CPC A63B 71/0605 (2013.01) [A63B 24/0021 (2013.01); G06T 7/248 (2017.01); G06V 10/25 (2022.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/42 (2022.01); A63B 2024/0025 (2013.01); A63B 2024/0028 (2013.01); A63B 2024/0034 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30224 (2013.01); G06T 2207/30228 (2013.01)] | 28 Claims |
|
1. A system, comprising:
an image capturing unit, configured to capture a plurality of input images, the plurality of images depicting a two-dimensional representation of a playing field;
an object detection module, configured to utilize computer vision techniques to detect a plurality of objects in the input images, the plurality of objects comprising at least two players, and a ball, using bounding boxes;
an object tracking module, configured to utilize computer vision techniques to track a change in the position of the plurality of objects across at least one input image, among the plurality of input images;
a simulation module, configured to:
simulate a location of each object, among the plurality of objects, on the playing field, by using depth estimation on the plurality of input images, to render a three-dimensional representation of the playing field;
identify x-axis, y-axis, and z-axis coordinates of the plurality of objects based on the depth estimation;
divide a front wall of the playing field into a plurality of attacking sections;
determine a relevant attacking section, among the plurality of attacking sections, based on the x-axis, y-axis, and z-axis coordinates of the ball;
divide a floor of the playing field into a plurality of segments; and
determine at least one relevant segment, among the plurality of segments, based on the x-axis, y-axis, and z-axis coordinates of the at least two players and/or the ball;
a metric module, configured to calculate at least one metric based on the coordinates of one or more objects, among the plurality of objects across the at least one input image; and
a decision-making module, employing at least one artificial intelligence model, configured to render a decision based on:
the at least one metric;
the relevant attacking section;
the at least one relevant segment; and
one or more rules correlating the decision to the at least one metric, the relevant attacking section, and the at least one relevant segment.
|