# US 2026/0087902 A1 · Systems and methods for detecting game assets for wagering game applications > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0087902 A1 - Document ID: US20260087902A1 - Status: Published application - Kind: A1 - Application number: 18/898,046 - Filed: 2024-09-26 - Published: 2026-03-26 - Earliest claimed: 2024-09-24 - Assignees: Aristocrat Technologies, Inc. - Applicants: Aristocrat Technologies, Inc. - Inventors: Robert Butler; Eric Santana; Jeannie Chiem - Web page: https://patentgrep.com/patent/US20260087902A1 ## CPC - G07F 17/322: {Casino tables, e.g. tables having integrated screens, chip detection means} - G06T 3/60: Rotation of whole images or parts thereof - G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215) - G06T 7/60: Analysis of geometric attributes - G06T 7/73: using feature-based methods - G06T 7/90: Determination of colour characteristics - G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion - G06V 10/56: relating to colour - G06V 10/764: using classification, e.g. of video objects - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/82: using neural networks - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - G06V 30/153: {using recognition of characters or words} - G07F 17/3241: {Security aspects of a gaming system, e.g. detecting cheating, device integrity, surveillance (computer security G06F21/00)} - G07F 17/3288: {Betting, e.g. on live events, bookmaking} - G07F 17/3293: {Card games, e.g. poker, canasta, black jack} - G06T 2207/10016: Video; Image sequence - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20112: Image segmentation details - G06T 2207/30242: Counting objects in image - G06T 2210/12: Bounding box - G07F: COIN-FREED OR LIKE APPARATUS (coin sorting G07D3/00; coin testing G07D5/00; {handling coins or paper currencies apart from payment activated apparatus G07D; payment architectures, schemes or protocols G06Q20/00}) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A system for detecting game assets for wagering game applications may include a storage device and/or circuitry. The storage device may be configured to store data representing an image of a roulette wheel spin. The circuitry may be configured to rotate the image represented by the data to align with a reference position and to identify attributes of the roulette wheel spin based at least in part on the image by implementing an artificial intelligence model comprising an object detection model. The circuitry may also be configured to predict, via the object detection model, which slot of a roulette wheel catches a roulette ball during the roulette wheel spin based at least in part on the attributes. The circuitry may be further configured to account for a number corresponding to the slot of the roulette wheel in a wagering game application. Various other systems and methods are also disclosed. ## Claims ### Claim 1 A system comprising: at least one storage device configured to store data that represents at least one image of a roulette wheel spin; and circuitry configured to: rotate at least a portion of the image represented by the data to align with a reference position associated with a roulette wheel; identify one or more attributes of the roulette wheel spin based at least in part on the image by implementing an artificial intelligence (AI) model comprising an object detection model; predict, via the object detection model, which slot of the roulette wheel catches a roulette ball during the roulette wheel spin based at least in part on the attributes; and account for a number corresponding to the slot of the roulette wheel in a wagering game application. ### Claim 2 (depends on 1) The system of claim 1, wherein the circuitry is further configured to detect the slot into which the roulette ball lands as part of the roulette wheel spin via the object detection model. ### Claim 3 (depends on 2) The system of claim 2, wherein the circuitry is further configured to detect the slot into which the roulette ball lands while the roulette wheel is spinning. ### Claim 4 (depends on 1) The system of claim 1, wherein the object detection model is trained by training data comprising at least one of: images of roulette wheel spins captured at different angles over roulette wheels; images of roulette wheel spins in which roulette balls land in different slots; or images of roulette wheel spins in which roulette balls caught in different slots are rotated to different positions around roulette wheels. ### Claim 5 (depends on 1) The system of claim 1, wherein the circuitry is further configured to rotate the portion of the image by: identifying an initial position of the slot as represented in the image; determining an angle between the initial position of the slot and the reference position relative to a center of the roulette wheel; and rotating the portion of the image to align with the reference position based at least in part on the angle. ### Claim 6 (depends on 5) The system of claim 5, wherein the circuitry is further configured to calculate the angle by applying at least one trigonometric function that involves the center of the roulette wheel, the initial position of the slot, and the reference position. ### Claim 7 (depends on 6) The system of claim 6, wherein the trigonometric function comprises an inverse cosine function that involves squared values of: a first distance between the reference position and the initial position of the slot; a second distance between the center of the roulette wheel and the slot; and a third distance between the center of the roulette wheel and the reference position. ### Claim 8 (depends on 7) The system of claim 7, wherein the circuitry is further configured to calculate the angle by: multiplying the second distance by the third distance; doubling a product of the multiplication; dividing a sum of the squared values by the doubled product; and applying a quotient of the division to the inverse cosine function. ### Claim 9 (depends on 1) The system of claim 1, wherein the circuitry is further configured to: crop the portion of the image around the number corresponding to the slot; and identify the number corresponding to the slot based at least in part on the cropped portion of the image. ### Claim 10 (depends on 1) The system of claim 1, wherein: the storage device is further configured to store a video of the roulette wheel spin; and the circuitry is further configured to: convert the video into multiple still images of the roulette wheel spin; and store the multiple still images in the storage device for use in predicting which slot catches the roulette ball during the roulette wheel spin. ### Claim 11 (depends on 10) The system of claim 10, wherein the circuitry is further configured to: identify at least one of the multiple still images that depicts the roulette ball moving around a ball track that surrounds the roulette wheel; and prevent the at least one of the multiple still images from being used to identify the attributes of the roulette wheel spin. ### Claim 12 (depends on 1) The system of claim 1, wherein: the AI model comprises a classification model; and the circuitry is further configured to identify the number corresponding to the slot into which the roulette ball lands via the classification model. ### Claim 13 (depends on 12) The system of claim 12, wherein the classification model is trained by training data comprising at least one of: images of numbers captured at different angles; images of numbers captured in environments of varied lighting; images of numbers captured with backgrounds of different colors; images of numbers shown in different colors; or images of numbers captured with different clarities or resolutions. ### Claim 14 (depends on 12) The system of claim 12, wherein the circuitry is further configured to generate a score that represents a probability of the number having been identified correctly via the classification model. ### Claim 15 A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the processor to: rotate at least a portion of an image of a roulette wheel spin to align with a reference position associated with a roulette wheel; identify one or more attributes of the roulette wheel spin based at least in part on the image of the roulette wheel spin by implementing an artificial intelligence (AI) model comprising an object detection model; predict, via the object detection model, which slot of the roulette wheel catches a roulette ball during the roulette wheel spin based at least in part on the attributes; and account for a number corresponding to the slot of the roulette wheel in a wagering game application. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more computer-executable instructions, when executed by the at least one processor of the computing device, further cause the processor to detect the slot into which the roulette ball lands as part of the roulette wheel spin via the object detection model. ### Claim 17 (depends on 16) The non-transitory computer-readable medium of claim 16, wherein the one or more computer-executable instructions, when executed by the at least one processor of the computing device, further cause the processor to detect the slot into which the roulette ball lands while the roulette wheel is spinning. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the object detection model is trained by training data comprising at least one of: images of roulette wheel spins captured at different angles over roulette wheels; images of roulette wheel spins in which roulette balls land in different slots; or images of roulette wheel spins in which roulette balls caught in different slots are rotated to different positions around roulette wheels. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more computer-executable instructions, when executed by the at least one processor of the computing device, further cause the processor to rotate the portion of the image by: identifying an initial position of the slot as represented in the image; determining an angle between the initial position of the slot and the reference position relative to a center of the roulette wheel; and rotating the portion of the image to align with the reference position based at least in part on the angle. ### Claim 20 A method comprising: rotating, by circuitry included in a computing system, at least a portion of an image of a roulette wheel spin to align with a reference position associated with a roulette wheel; identifying, by the circuitry, one or more attributes of the roulette wheel spin based at least in part on the image of the roulette wheel spin by implementing an artificial intelligence (AI) model comprising an object detection model; predicting, by the circuitry via the object detection model, which slot of the roulette wheel catches a roulette ball during the roulette wheel spin based at least in part on the attributes; and accounting for a number corresponding to the slot of the roulette wheel in a wagering game application.