# US 10,121,065 B2 · Athletic attribute determinations from image data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,065 B2 - Document ID: US10121065B2 - Status: Granted - Kind: B2 - Application number: 14/773,946 - Filed: 2014-03-14 - Published: 2016-05-05 - Granted: 2018-11-06 - Earliest claimed: 2013-03-14 - Assignees: NIKE, Inc. - Applicants: NIKE Inc. - Inventors: Jeffrey Ota; Vikram Malhotra; Jay Meschter; James Molyneux; Kristopher L. Homsi; Paul Winsper - Web page: https://patentgrep.com/patent/US10121065B2 ## CPC - G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) - G06F 18/24: Classification techniques - G06V 40/23: {Recognition of whole body movements, e.g. for sport training} - G06T 2207/10016: Video; Image sequence - G06T 2207/30196: Human being; Person - G06T 2207/30221: Sports video; Sports image - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems and methods for determining athletic attributes are disclosed. Aspects of this disclosure relate to determining athletic attributes of an athlete from image data. One or more determinations may be based alterations of image data between different images, such as alterations in pixels representing objects or portions of objects. Image data may be utilized to determine whether certain thresholds are met. Various threshold levels may be applied to one or more objects represented in the image data. Landmarks/distance calibrations may be utilized from time-stamped image data to allow for precise measuring of performance (including, but not limited to: sprint or agility times, flight time for vertical jump, distance for throws). Data retrieved or derived from the image data may be used in scoring and/or ranking athletes. Such data may be used to provide training advice or regimes to the athletes or other individuals, such as coaches or trainers. ## Claims ### Claim 1 A computer-implemented method for determining an athletic attribute of an athlete comprising: initiating a first trigger, the first trigger configured to indicate to an athlete to initiate performance of a predefined physical activity; responsive to initiating the first trigger, initiating capturing a plurality of sequential images with a first camera; determining a first image, within the plurality of sequential images, that correlates to a timing of the initiating of the first trigger; automatically associating a trigger flag with the first image; processing a plurality of sequential images to identify an initiation image, the processing comprising: identifying pixels in the plurality of sequential images that correspond to a specific first body portion of an athlete, wherein the first body portion is selected based upon a predetermined physical activity the athlete is to perform; and determining, based upon the identified pixels, whether the pixels are altered between a plurality of images within the plurality of sequential images such that the alteration satisfies a first body portion movement quality threshold; determining a reaction value for the athlete based upon a duration between the first image and the initiation image, utilizing the initiation image in a determination of at least one performance attribute of the athlete; and calculating a rating of the athlete based on the at least one performance attribute. ### Claim 2 (depends on 1) The method of claim 1, further comprising: processing at least a portion of the plurality of sequential images to locate completion image comprising image data of the athlete completing the predetermined physical activity; and calculating a physical activity duration based upon the initiation image and the completion image. ### Claim 3 (depends on 2) The method of claim 2, wherein the attribute is at least one of: speed, endurance, and combinations thereof. ### Claim 4 (depends on 1) The method of claim 1, wherein the processing of the plurality of sequential images comprises the utilization of an optical flow process. ### Claim 5 (depends on 3) The method of claim 3, wherein an output of the optical flow process is provided as an input to a process comprising: providing flow field data comprising a pixel-distance change of an identified object from a first image to a second image; and using the flow field data to identify a specific type of motion of the athlete represented in the plurality of sequential images during performance of the predetermined physical activity. ### Claim 6 (depends on 5) The method of claim 5, further comprising: using the identified specific type of motion to identify an action comprising at least one of: initiation of the activity, acceleration, velocity, tempo, distance travelled by an object, or completion of the activity. ### Claim 7 (depends on 4) The method of claim 4, wherein a first frame rate between a first set two images within the plurality of sequential images is different than a second frame rate between a second set of images within the plurality of sequential images, the method further comprising: quantifying an accurate time between the images having the first frame rate and an accurate time between images having the second time frame rate; and utilizing the accurate time in the optical flow process. ### Claim 8 (depends on 1) The method of claim 1, further comprising: initiating a second trigger to indicate to the athlete to perform a predefined movement during performance of the physical activity; determining a second image, of the plurality of images, that correlates to a timing of the second trigger; associating a second trigger flag with the second image; associating a third flag with a third image correlating to the athlete performing the predefined movement; and determining a second reaction value for the athlete based upon the duration between the second image and the third image. ### Claim 9 (depends on 1) The method of claim 1, further comprising: utilizing the reaction value and the performance attribute in a sport-specific ranking algorithm to obtain a single athletic score for the athlete. ### Claim 10 (depends on 1) The method of claim 1, wherein a first frame rate between a first set of two images between the first image and the initiation image is different than a second frame rate between a second set of two images between the first image and the initiation image, the method further comprising: accounting for different frame rates when determining the time duration. ### Claim 11 (depends on 1) The method further of claim 1, further comprising: receiving sensor data from a sensor operatively attached to the athlete during performance of the physical activity; and utilizing the sensor data to conduct image stabilization upon at least a portion of the plurality of sequential images before identifying the movement quality threshold. ### Claim 12 (depends on 1) The method of claim 1, further comprising: receiving sensor data from a sensor operatively attached to the athlete during performance of the physical activity; and utilizing the sensor data in conjunction with an optical flow process to identify at least one of the initiation image and an end image. ### Claim 13 An apparatus comprising: one or more processors; memory storing computer executable instructions that, when executed by the one or more processors, cause the apparatus to: initiate a first trigger, the first trigger configured to indicate to an athlete to initiate performance of a predefined physical activity; responsive to initiating the first trigger, initiate capturing a plurality of sequential images with a first camera; determine a first image, within the plurality of sequential images, that correlates to a timing of the initiating of the first trigger; automatically associate a trigger flag with the first image; process a plurality of sequential images to identify an initiation image by: identifying pixels in the plurality of sequential images that correspond to a specific first body portion of an athlete, wherein the first body portion is selected based upon a predetermined physical activity the athlete is to perform; and determining, based upon the identified pixels, whether the pixels are altered between a plurality of images within the plurality of sequential images such that the alteration satisfies a first body portion movement quality threshold; determine a reaction value for the athlete based upon a duration between the first image and the initiation image; utilize the initiation image in a determination of a performance attribute of the athlete; and calculate a rating of the athlete based on the performance attribute. ### Claim 14 (depends on 13) The apparatus of claim 13, the memory storing computer executable instructions that, when executed by the one or more processors, cause the apparatus to: process at least a portion of the plurality of sequential images to locate a completion image comprising image data of the athlete completing the predetermined physical activity; and calculate a physical activity duration based upon the initiation image and the completion image. ### Claim 15 (depends on 14) The apparatus of claim 14, wherein an output of the optical flow process is provided as an input to a process comprising: providing flow field data comprising a pixel-distance change of an identified object from a first image to a second image; and using the flow field data to identify a specific type of motion of the athlete represented in the image data during performance of the predetermined physical activity. ### Claim 16 (depends on 15) The apparatus of claim 15, the memory storing computer executable instructions that, when executed by the one or more processors, cause the apparatus to: use the identified specific type of motion to identify an action comprising at least one of: initiation of the activity, acceleration, velocity, tempo, distance travelled by an object, or completion of the activity. ### Claim 17 (depends on 13) The apparatus of claim 13, wherein the processing of the plurality of images comprises the utilization of an optical flow process. ### Claim 18 A system comprising: a first computing device configured to: initiate a first trigger, the first trigger configured to indicate to an athlete to initiate performance of a predefined physical activity; responsive to initiating the first trigger, initiate capturing a plurality of sequential images with a first camera; determine a first image, within the plurality of sequential images, that correlates to a timing of the initiating of the first trigger; automatically associate a trigger flag with the first image; process a plurality of sequential images to identify an initiation image by: identifying pixels in the plurality of sequential images that correspond to a specific first body portion of an athlete, wherein the first body portion is selected based upon a predetermined physical activity the athlete is to perform; and determining, based upon the identified pixels, whether the pixels are altered between a plurality of images within the plurality of sequential images such that the alteration satisfies a first body portion movement quality threshold; determine a reaction value for the athlete based upon a duration between the first image and the initiation image; utilize the initiation image in a determination of a performance attribute of the athlete; and calculate a rating of the athlete based on the performance attribute; and a second computing device configured to receive the first trigger. ### Claim 19 (depends on 18) The system of claim 18, the first computing device further configured to: process at least a portion of the plurality of sequential images to locate a completion image comprising image data of the athlete completing the predetermined physical activity; and calculate a physical activity duration based upon the initiation image and the completion image. ### Claim 20 (depends on 18) The system of claim 18, wherein the processing of the plurality of images comprises the utilization of an optical flow process.