IP Library Granted Patent US 12,450,902
Granted Patent B2
US 12,450,902 · App. 18/331,100 · Granted Oct 21, 2025

Systems, methods, and computer-program products for assessing athletic ability and generating performance data

Inventors: Corey Leon Yates (Roswell, GA); Alfonzo Thurman, II (Snellville, GA)
Assignee: Recruiting Analytics LLC
G06V20/42A61B5/1118A61B5/1128A61B5/117A63B24/0003A63B24/0021A63B24/0062G06T7/248G06V40/25A61B2503/10G06T2207/30221
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,450,902
App. No.
18/331,100
Granted
Oct 21, 2025
Kind
B2
Abstract

Methods, systems, and computer-program products used for assessing athletic ability and generating performance data. In one embodiment, athlete performance data is generated through computer-vision analysis of video of an athletic performing, e.g., during practice or gameplay. The generated performance data for the athlete may include, for example, maximum speed, maximum acceleration, time to maximum speed, transition time (e.g., time to change direction), closing speed (e.g., time to close the distance to another athlete), average separation (e.g., between the athlete and another athlete), play-making ability, athleticism (e.g., a weighted computation and/or combination of multiple metrics), and/or other performance data. This performance data may be used to generate and/or update a profile associated with the athlete, which can be utilized for recruiting, scouting, comparing, and/or assessing athletes with greater efficiency and precision.

Claims (52)

1. A computer-implemented method for generating athlete performance data using computer-vision analysis and identifying athletes with desired characteristics, the method comprising:

accessing a video, the video comprising a plurality of frames depicting an athlete, each of the plurality of frames having an associated time-stamp;

identifying, using a computer-vision system, a location designator associated with the athlete in each frame of the plurality of frames;

identifying, using the computer-vision system, a location designator associated with a reference element in each frame of the plurality of frames;

identifying, using the computer-vision system, a coordinate distance between the location designator associated with the athlete and the location designator associated with the reference element in each frame of the plurality of frames;

converting, using the computer-vision system, each coordinate distance to a corresponding physical distance;

generating performance data for the athlete using the converted physical distance at each time-stamp;

updating an athlete profile associated with the athlete to include the generated performance data;

receiving at least one user-selected parameter associated with at least one desired characteristic;

selecting the athlete profile from a plurality of athlete profiles based on the at least one user-selected parameter; and

identifying the athlete profile as a best-fit match with the at least one user-selected parameter.

2. The computer-implemented method of claim 1 , wherein the generated performance data comprises a maximum speed of the athlete.

3. The computer-implemented method of claim 1 , wherein the converting of each coordinate distance to the corresponding physical distance is performed using a transformation matrix, a calibration factor, and/or a conversion factor.

4. The computer-implemented method of claim 1 , wherein the reference element comprises a game ball.

5. The computer-implemented method of claim 4 , wherein the generated performance data comprises at least a speed of the game ball.

6. The computer-implemented method of claim 4 , wherein the generated performance data comprises at least an acceleration of the game ball.

7. The computer-implemented method of claim 4 , wherein the generated performance data comprises at least a trajectory of the game ball.

8. The computer-implemented method of claim 1 , wherein the location designator associated with the athlete is a first digital bounding box and wherein the location designator associated with the reference element is a second digital bounding box.

9. The computer-implemented method of claim 1 , wherein the generated performance data comprises a maximum speed of the athlete at a particular point in time during gameplay.

10. The computer-implemented method of claim 1 , wherein the generated performance data comprises a maximum speed of the athlete along a particular distance traveled during gameplay.

11. The computer-implemented method of claim 1 , further comprising performing a data filtering process prior to generating the athlete performance data.

12. The computer-implemented method of claim 1 , further comprising displaying the generated performance data in connection with the athlete.

13. A computer-implemented method for generating athlete performance data using computer-vision analysis and identifying athletes with desired characteristics, the method comprising:

accessing a video, the video comprising a plurality of frames depicting an athlete, each of the plurality of frames having an associated time-stamp;

identifying, using a computer-vision system, a location designator associated with an athlete in each frame of the plurality of frames;

identifying, using the computer-vision system, a location designator associated with a game ball in each frame of the plurality of frames;

identifying, using the computer-vision system, a selection of frames of the plurality of frames during which the game ball is traveling to the athlete or during which the game ball is traveling from the athlete;

identifying, using the computer-vision system, a coordinate distance between the location designator associated with the athlete and the location designator associated with the game ball in each frame of the selection of the plurality of frames;

converting, using the computer-vision system, each coordinate distance to a corresponding physical distance;

generating performance data for the athlete using each converted physical distance;

updating an athlete profile associated with the athlete to include the generated performance data;

receiving at least one user-selected parameter associated with at least one desired characteristic;

selecting the athlete profile from a plurality of athlete profiles based at least in part on a comparison of the at least one user-selected parameter and the athlete profile including the generated performance data thereof; and

identifying the athlete profile as a best-fit match with the at least one user-selected parameter.

14. The computer-implemented method of claim 13 , wherein the converting is performed using a transformation matrix, a calibration factor, and/or a conversion factor.

15. The computer-implemented method of claim 13 , wherein the game ball is a football.

16. The computer-implemented method of claim 13 , wherein the game ball is a basketball.

17. The computer-implemented method of claim 13 , wherein the game ball is a baseball.

18. A computer-implemented method for generating athlete performance data using computer-vision analysis and identifying athletes with desired characteristics, the method comprising:

accessing a video, the video comprising a plurality of frames depicting an athlete, each of the plurality of frames having an associated time-stamp;

identifying, using a computer-vision system, a location designator associated with an athlete in each frame of the plurality of frames;

identifying, using the computer-vision system, a location designator associated with a reference element in each frame of the plurality of frames;

identifying, using the computer-vision system, a coordinate distance between the location designator associated with the athlete and the location designator associated with the reference element in each frame of the plurality of frames;

converting, using the computer-vision system, each coordinate distance to a corresponding physical distance;

generating performance data for the athlete using the converted physical distance at each time-stamp;

averaging the generated performance data with prior-generated athlete performance data stored in an athlete profile associated with the athlete to thereby generate averaged performance data for the athlete;

updating the athlete profile associated with the athlete to include the averaged performance data;

receiving at least one user-selected parameter associated with at least one desired characteristic;

selecting the athlete profile from a plurality of athlete profiles based at least in part on a comparison of the at least one user-selected parameter and the athlete profile including the averaged performance data thereof; and

identifying the athlete profile as a best-fit match with the at least one user-selected parameter.

19. The computer-implemented method of claim 18 , wherein the athlete comprises a first athlete, and wherein the reference element comprises a second athlete, and wherein the averaged performance data comprises at least one of average play completion rate, average separation, and/or average closing time.

20. The computer-implemented method of claim 18 , wherein the reference element comprises a game ball.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 28, 2024
From: YATES, COREY LEON; THURMAN, ALFONZO, II
To: RECRUITING ANALYTICS LLC
Reel/Frame 067875/0770 →
Continuity (5)
Continuation 17002331 · Aug 25, 2020
Provisional Application 63011976 · Apr 17, 2020
Provisional Application 62987809 · Mar 10, 2020
Provisional Application 62985316 · Mar 4, 2020
Related Publication 20230316750A1 · Oct 5, 2023
References Cited (34)
US 6710713B1 · Russo · 2004 [cited by applicant]
US 9486693B2 · Regan et al. · 2016 [cited by applicant]
US 9824281B2 · Roshtkhari et al. · 2017 [cited by applicant]
US 9977966B2 · Zakaluk · 2018 [cited by applicant]
US 10402655B2 · Javan Roshtkhari et al. · 2019 [cited by applicant]
US 10430953B2 · Roshtkhari Javan et al. · 2019 [cited by applicant]
US 11157742B2 · Zhang et al. · 2021 [cited by applicant]
US 11710317B2 · Yates · 2023 [cited by examiner]
US 20060132487A1 · Sada et al. · 2006 [cited by applicant]
US 20110013836A1 · Gefen et al. · 2011 [cited by applicant]
US 20170109015A1 · Krasadakis · 2017 [cited by applicant]
US 20180336704A1 · Javan Roshtkhari et al. · 2018 [cited by applicant]
US 20190091541A1 · Schulte et al. · 2019 [cited by applicant]
US 20190251366A1 · Zhong et al. · 2019 [cited by applicant]
KR 20180063777A · 2018 [cited by applicant]
Sanford, R., et al., “Group Activity Detection from Trajectory and Video Data in Soccer”, In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1-9 (2020). [cited by applicant]
Gavrilyuk, K. et al., “Actor-Transformers for Group Activity Recognition”, In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 839-848 (2020). [cited by applicant]
Mehrasa, N., et al., “Learning Person Trajectory Representations for Team Activity Analysis”, arXiv:1706.00893v1, pp. 1-9 (Jun. 3, 2017). [cited by applicant]
Zhai, M., et al., “Deep learning of appearance models for online object tracking”, In Proceedings of the European Conference on Computer Vision (ECCV), pp. 1-6 (2018). [cited by applicant]
Zhong, Y. et al., “Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction”, arXiv:1808.04063v2, pp. 1-10 (Aug. 14, 2018). [cited by applicant]
Liu, G., and Schulte, O., “Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation”, arXiv:1805.11088v3, pp. 1-7 (Jul. 16, 2018). [cited by applicant]
Schulte, O., et al., “A Markov Game model for valuing actions, locations, and team performance in ice hockey”, Data Mining and Knowledge Discovery, vol. 31, pp. 1-24 (Mar. 24, 2017). [cited by applicant]
Schulte, O., et al., “Apples-to-Apples: Clustering and Ranking NHL Players Using Location Information and Scoring Impact”, MIT Sloan Sports Analytics Conference, pp. 1-14 (2017). [cited by applicant]
Silva, R. M. et al., “The evaluation of pace of play in hockey”, Journal of Sports Analytics, vol. 4, pp. 145-151 (2018). [cited by applicant]
Homayounfar, N. et al., “Sports Field Localization via Deep Structured Models”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5212-5220 (2017). [cited by applicant]
Fani, M., et al., “Hockey Action Recognition via Integrated Stacked Hourglass Network”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 29-37 (2017). [cited by applicant]
Tora, M. R. et al., “Classification of Puck Possession Events in Ice Hockey”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 91-98 (2017). [cited by applicant]
Khodabandeh, M., et al., “Discovering Human Interactions in Videos with Limited Data Labelling”, In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 9-18 (2015). [cited by applicant]
Deng, Z., et al., “Deep Structured Models for Group Activity Recognition”, arXiv:1506.04191v1, pp. 1-12 (Jun. 12, 2015). [cited by applicant]
Horton, M., “Learning Feature Representations from Football Tracking”, MIT Sloan Sports Analytics Conference, pp. 1-14 (2020). [cited by applicant]
Keane, E., et al., Data-driven lowlight and highlight reel creation based on explainable temporal game models, MIT Sloan Sports Analytics Conference, pp. 1-15 (2019). [cited by applicant]
Yu, D., et al., “Playing Fast Not Loose: Evaluating team-level pace of play in ice hockey using spatio-temporal possession data”, arXiv preprint arXiv: 1902.02020, pp. 1-28 (2019). [cited by applicant]
Czuzoj-Shulman, N., et al., “Winning Isn't Everything: A contextual analysis of hockey face-offs”, MIT Sloan Sports Analytics Conference, pp. 1-18 (2019). [cited by applicant]
Roshtkhari, M. J., and Levine, M. D., “Chapter 2.3: Tracking Without Appearance Descriptors”, Abstract. Handbook of Pattern Recognition and Computer Vision, pp. 1-2 (2016). [cited by applicant]