Gaming activity monitoring systems and methods
Embodiments relate to systems, methods and computer readable media for gaming monitoring. In particular, embodiments process images to determine presence of a gaming object on a gaming table in the images. Embodiments estimate postures of one or more players in the images and based on the estimated postures determine a target player associated with the gaming object among the one or more players.
1. A method for monitoring gaming activity in a gaming area comprising a gaming table, the method comprising:
providing at least one camera configured to capture images of the gaming area, at least one processor configured to communicate with the at least one camera and a memory storing instructions executable by the at least one processor;
determining by the at least one processor, a presence of a first gaming object on the gaming table in a first image from a series of images of the gaming area captured by the at least one camera, the series of images comprising one or more images;
responsive to determining the presence of the first gaming object in the first image, processing by the at least one processor the first image to estimate postures of one or more players;
based on the estimated postures, determining by the at least one processor a first target player associated with the first gaming object among the one or more players.
2. The method of claim 1 , further comprising identifying by the at least one processor in the series of images an image region of a face of the first target player associated with the first gaming object.
3. The method of claim 1 , wherein estimating postures of one or more players in the first image comprises identifying one or more periphery indicator regions in the first image, each periphery indicator region corresponding to a distal hand periphery of one or more players.
4. The method of claim 3 , wherein each of the one or more periphery indicator regions corresponds to a distal left hand periphery or a distal right hand periphery.
5. The method of claim 1 , further comprising determining by the at least one processor the first target player associated with the first gaming object by:
estimating a distance of each periphery indicator region from the first gaming object in the first image;
identifying a closest periphery indicator region based on the estimated distance; and
determining the first target player associated with the first gaming object based on the identified closest periphery indicator region.
6. The method of claim 5 , wherein processing by the at least one processor the first image to estimate postures comprises estimating a skeletal model of one or more player, and wherein determining the first target player associated with the first gaming object is based on the estimated skeletal model of one or more player.
7. The method of claim 6 , wherein estimating the skeletal model of one or more player comprises estimating key points in the first image associated with one or more of: wrists, elbows, shoulders, neck, nose, eyes or ears of the one or more players.
8. The method of claim 1 , further comprising:
determining by the at least one processor, a presence of a second gaming object on the gaming table in a second image from the series of images;
responsive to determining the presence of the second gaming object in the second image, process by the at least one processor the second image to estimate postures of one or more players;
based on the estimated postures, determine by the at least one processor, a second target player associated with the second gaming object among the one or more players.
9. The method of claim 1 , wherein the first gaming object comprises any one of: a game object, a token, a currency note or a coin.
10. The method of claim 1 , wherein the memory comprises one or more posture estimation machine learning models trained to estimate postures of one or more players in the series of images.
11. The method of claim 10 , wherein the one or more posture estimation machine learning models comprise one or more deep learning artificial neural networks trained to estimate postures of one or more players in the captured images.
12. The method of claim 2 , wherein identifying by the at least one processor an image region of a face of the first target player comprises extracting a vector representation of the face of the first target player using a face recognition machine learning model stored in the memory.
13. The method of claim 1 , further comprising estimating by the at least one processor a game object value associated with the first gaming object.
14. The method of claim 1 , wherein determining presence of a first gaming object on the gaming table further comprises determining a gaming table zone associated with the first gaming object.
15. The method of claim 1 , further comprising identifying in the series of images a plurality of face regions corresponding to a face of the first target player associated with the first gaming object.
16. The method of claim 15 , further comprising processing the plurality of face regions to determine face orientation information of the first target player's face in each of the plurality of face regions.
17. The method of claim 16 , further comprising processing the face orientation information of the first target player's face in each of the plurality of face regions to determine a most head-on face region corresponding to the target player.
18. The method of claim 1 , wherein the captured images comprise depth of field images; and
determination of a presence of a first gaming object on the gaming table is based on the depth of field images.
19. Non-transient computer readable storage media storing program code, the program code executable by at least one processor to configure the at least one processor to perform the method of claim 1 .