Back to results
US 12,499,730 B2Granted
Systems, methods and devices for monitoring betting activities
AssigneeArb Labs Inc.
InventorsAdrian Bulzacki, Vlad Cazan
Life of this patent
Estimating the term…
Abstract
System, processes and devices for monitoring betting activities using bet recognition devices and a server. Each bet recognition device has an imaging component for capturing image data for a gaming table surface. The bet recognition device receives calibration data for calibrating the bet recognition device. A server processor coupled to a data store processes the image data received from the bet recognition devices over the network to detect, for each betting area, a number of chips and a final bet value for the chips.
Claims20
A system for monitoring game activities at a gaming table having at least one betting area, the system comprising:
- one or more client hardware devices positioned to capture image data of one or more chips within the at least one betting area of the gaming table from respective positions;
- a communication link configured for transmitting the captured image data;
- and a processor configured to:
- retrieve the captured image data from the one or more client hardware devices via the communication link;
- process the captured image data to identify a chip stack region having at least one of the one or more chips;
- process the captured image data to determine one or more depth values corresponding to one or more distances from a reference point to one or more of the one or more chips;
- detect one or more specific chips of the at least one of the one or more chips within the chip stack region by using the one or more depth values, and by using the one or more depth values to identify one or more chips outside the chip stack region;
- for each respective detected specific chip of the one or more specific chips:
- generate one or more histograms of the respective detected specific chip;
- and
- estimate a chip value of the respective detected specific chip as a reference chip value associated with a reference histogram having a greatest similarity to the one or more histograms of the respective detected specific chip, the reference histogram being from a library of reference histograms;
- generate an output data structure storing one or more data fields representative of the chip value of each of the detected one or more specific chips;
- and
- transmit the output data structure and a control command to a front end interface device for displaying the one or more data fields representative of the chip value of each ofthe detected one or more specific chips;
- wherein, for each individual betting area of the at least one betting area, the library of reference histograms is developed as part of a calibration process using a calculated red green blue (RGB) depth bounding area based at least on one or more depth values for the individual betting area and real-world images of chips within the individual betting area to train a base set of features for a machine learning process to dynamically associate and create linkages as new chip types are introduced;
- wherein the estimation of the chip value based on the reference histogram is based at least on the trained base set of features;
- and
- wherein the one or more depth values corresponding to the one or more distances from the reference point to the one or more of the one or more chips are determined by measuring stereo parallax, shadow measurements, light intensity measurements, relative size measurements, and illumination grid measurements.
15 more elements
A method for monitoring game activities at a gaming table having at least one betting area, the method comprising:
- retrieving captured image data of one or more chips within the at least one betting area of the gaming table from one or more client hardware devices positioned to capture the image data from respective positions via a communication link;
- processing the captured image data to identify a chip stack region having at least one of the one or more chips;
- processing the captured image data to determine one or more depth values corresponding to one or more distances from a reference point to one or more of the one or more chips;
- detecting one or more specific chips of the at least one of the one or more chips within the chip stack region by using the one or more depth values to represent each specific chip of the one or more specific chips, and by using the one or more depth values to identify one or more chips outside the chip stack region;
- for each respective detected specific chip of the one or more specific chips:
- generating one or more histograms of the respective detected specific chip;
- and
- estimating a chip value of the respective detected specific chip as a reference chip value associated with a reference histogram having a greatest similarity to the one or more histograms of the respective detected specific chip, the reference histogram being from a library of reference histograms;
- generating an output data structure storing one or more data fields representative of the chip value of each of the detected one or more specific chips;
- and transmitting
- the output data structure and a control command to a front end interface device for displaying the one or more data fields representative of the chip value of each of the detected one or more specific chips;
- wherein, for each individual betting area of the at least one betting area, the library of reference histograms is developed as part of a calibration process using a calculated red green blue (RGB) depth bounding area based at least on one or more depth values for the individual betting area and real-world images of chips within the individual betting area to train a base set of features for a machine learning process to dynamically associate and create linkages as new chip types are introduced;
- wherein the estimation of the chip value based on the reference histogram is based at least on the trained base set of features;
- and
- wherein the one or more depth values corresponding to the one or more distances from the reference point to the one or more of the one or more chips are determined by measuring stereo parallax, shadow measurements, light intensity measurements, relative size measurements, and illumination grid measurements.
12 more elements
A non-transitory computer readable medium storing machine-interpretable instructions, which when executed by a processor, cause the processor to perform a method for monitoring game activities at a gaming table having at least one betting area, the method comprising:
- retrieving captured image data of one or more chips within the at least one betting area of the gaming table from one or more client hardware devices positioned to capture the image data from respective positions via a communication link;
- processing the captured image data to identify a chip stack region having at least one of the one or more chips;
- processing the captured image data to determine one or more depth values corresponding to one or more distances from a reference point to one or more of the one or more chips;
- detecting one or more specific chips of the at least one of the one or more chips within the chip stack region by using the one or more depth values to represent each specific chip of the one or more specific chips, and by using the one or more depth values to identify one or more chips outside the chip stack region;
- for each respective detected specific chip of the one or more specific chips:
- generating one or more histograms of the respective detected specific chip;
- and estimating
- a chip value of the respective detected specific chip as a reference chip value associated with a reference histogram having a greatest similarity to the one or more histograms of the respective detected specific chip, the reference histogram being from a library of reference histograms;
- generating an output data structure storing one or more data fields representative of the chip value of each of the detected one or more specific chips;
- and transmitting
- the output data structure and a control command to a front end interface device for displaying the one or more data fields representative of the chip value of each of the detected one or more specific chips;
- wherein, for each individual betting area of the at least one betting area, the library of reference histograms is developed as part of a calibration process using a calculated red green blue (RGB) depth bounding area based at least on one or more depth values for the individual betting area and real-world images of chips within the individual betting area to train a base set of features for a machine learning process to dynamically associate and create linkages as new chip types are introduced;
- wherein the estimation of the chip value based on the reference histogram is based at least on the trained base set of features;
- and
- wherein the one or more depth values corresponding to the one or more distances from the reference point to the one or more of the one or more chips are determined by measuring stereo parallax, shadow measurements, light intensity measurements, relative size measurements, and illumination grid measurements.
12 more elements
Dependencies are inferred from the claim text.