System and method for automated table game activity recognition
Some embodiments relate to a system for automated gaming recognition, the system comprising: at least one image sensor configured to capture image frames of a field of view including a table game; at least one depth sensor configured to capture depth of field images of the field of view; and a computing device configured to receive the image frames and the depth of field images, and configured to process the received image frames and depth of field images in order to produce an automated recognition of at least one gaming state appearing in the field of view. Embodiments also relate to methods and computer-readable media for automated gaming recognition. Further embodiments relate to methods and systems for monitoring game play and/or gaming events on a gaming table.
1. A method of monitoring game play on a table surface of a gaming table, the method comprising:
analysing in real time by a computing device in communication with at least one camera configured to capture images of the table surface, captured images of the table surface to identify a presence of a game object in any one of a plurality of first regions of interest on the table surface;
in response to the game object being identified as present in the any one of a plurality of first regions of interest, recording a time stamp for a game event;
transmitting, by the computing device, game event data to a server, the game event data including the time stamp, an indication of the game event and an identifier of the any one of a plurality of first regions of interest;
capturing depth of field images of the table surface using at least one depth sensor; and
wherein the analysing includes
identifying one or more groups of wager objects in one or more second regions of interest,
estimating a height of each of the one or more groups of wager objects with respect to the table surface based on the captured depth of field images, and
estimating a number of wager objects present in each group of wager objects based on the estimated height of each of the one or more groups of wager objects with respect to the table surface; and
wherein the one or more groups of wager objects are different from the game object.
2. The method of claim 1 , wherein the game object is a game card or a position marker.
3. The method of claim 1 , wherein the analysing further comprises identifying a colour of an upper most wager object among each group of wager objects.
4. The method of claim 3 , further comprising:
automatically estimating a wager amount associated with each second region of interest in which at least one wager object is identified, wherein
the automatically estimating is based on the identified colour of the upper-most wager object among each group of wager objects and the estimated number of wager objects in each group of wager objects in a respective second region of interest.
5. The method of claim 1 , wherein the analysing in real time by a computing device comprises:
detecting one or more edges corresponding to the game object; and
approximating a contour of the one or more edges to a contour model to identify the game object.
6. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform the method of claim 1 .
7. A method of monitoring game play on a table surface of a gaming table, the method comprising:
analysing in real time by a computing device in communication with at least one camera configured to capture images of the table surface, captured images of the table surface to identify a presence of a game object in any one of a plurality of first regions of interest on the table surface;
in response to the game object being identified as present in the any one of a plurality of first regions of interest, recording a time stamp for a game event;
transmitting, by the computing device, game event data to a server, the game event data including the time stamp, an indication of the game event and an identifier of the any one of a plurality of first regions of interest;
wherein the captured images include multi-spectral images; and
wherein the analysing includes multi frame processing of the multi-spectral images to identify the presence of the game object in any one of the plurality of the first regions of interest or second regions of interest on the table surface.
8. A system of monitoring game play on a table surface of a gaming table, the system comprising:
at least one camera configured to capture images of the table surface; and
a computing device in communication with the at least one camera, said computing device configured to analyse, in real time, captured images of the table surface to automatically identify a presence of a game object in any one of a plurality of first regions of interest on the table surface;
wherein said at least one camera includes a depth sensing device to communicate, to the computing device, depth data of wager objects with respect to the table surface;
wherein said computing device is configured to
identify one or more groups of wager objects in one or more second regions of interest,
estimate a height of each of the one or more groups of wager objects with respect to the table surface based on the depth data of wager objects with respect to the table surface, and
estimate a number of wager objects present in each group of wager objects based on the estimated height of each of the one or more groups of wager objects with respect to the table surface; and
wherein the one or more groups of wager objects is different from the game object.
9. The system of claim 8 , wherein the game object is a game card or a position marker.
10. The system of claim 8 , wherein the computing device is further configured to identify a colour of an upper-most wager object among each group of wager objects.
11. The system of claim 10 , wherein
the computing device is further configured to automatically estimate a wager amount associated with each second region of interest in which at least one wager object is identified, and
the automatic estimate is based on the identified colour of the upper-most wager object among each group of wager objects and the estimated number of wager objects in each group of wager objects in a respective second region of interest.
12. The system of claim 8 , wherein the computing device is configured to analyse, in real time, the captured images of the table surface by
detecting one or more edges corresponding to the game object; and
approximating a contour of the one or more edges to a contour model to identify the game object.
13. A system of monitoring game play on a table surface of a gaming table, the system comprising:
at least one camera configured to capture images of the table surface; and
a computing device in communication with the at least one camera, said computing device configured to analyse, in real time, captured images of the table surface to automatically identify a presence of a game object in any one of a plurality of first regions of interest on the table surface;
wherein the captured images include multi-spectral images; and
wherein the computing device is configured to perform multi-frame processing of the multi-spectral images to identify the presence of the game object in any one of the plurality of the first regions of interest or second regions of interest on the table surface.