The Data-Driven Engineering in Athletics project brings together engineering, artificial intelligence, video analysis, sports biomechanics, exercise science, and community outreach. Students work alongside collaborators from several departments and organizations to develop responsible, practical methods for transforming athletic video and performance data into meaningful information for coaches and research partners.

Fall 2026 Opportunity	Time Commitment	Academic Credit
Research and outreach experience	126 total hours ~9 hours per week	CBE 498R or EXSC 399R

Students who successfully complete the Fall Semester experience may be considered for a future paid position in the lab. The broader Data-Driven Engineering in Athletics initiative began in 2024 and is expected to continue through 2030.

Research Statement

The Data-Driven Engineering in Athletics project develops and evaluates artificial-intelligence-assisted methods for analyzing human movement from authorized video and performance data. The research combines computer vision, pose estimation, biomechanics, engineering analysis, exercise science, data visualization, and responsible AI practices.

The project has two connected purposes:

1. Advance research and technology by improving the accuracy, reliability, interpretation, and practical use of AI-assisted biomechanical measurements.
2. Prepare students for interdisciplinary work by giving them experience with real data, collaborative research, technical communication, quality assurance, and responsible information management.

The project supports analysis of running, track and field, basketball, and other athletic movements. Research results are translated into video overlays, quantitative measurements, coach-facing reports, visualization tools, and educational resources.

Current collaborators include BYU Engineering, Intermountain Health, Utah Jazz Youth, exercise science researchers, software developers, Application Engineers, and coaching staffs throughout Utah.

Larger Project Objectives

1. Develop AI-Assisted Biomechanical Analysis

• Develop and improve computer-vision and pose-estimation methods for analyzing athletic movement.
• Extract meaningful measurements from running, sprinting, jumping, throwing, and basketball video.
• Evaluate camera position, frame rate, image quality, athlete visibility, and other factors that affect measurement reliability.
• Compare AI-generated measurements with established biomechanical principles and available reference measurements.

2. Establish Reliable Data and Quality-Assurance Workflows

• Create repeatable processes for receiving, organizing, labeling, processing, reviewing, and securely storing authorized videos.
• Identify video or data that cannot be analyzed reliably.
• Document model uncertainty, technical limitations, and potential sources of error.
• Treat AI-generated measurements as estimates that require informed human review.

3. Translate Analysis into Useful Coaching Information

• Convert technical measurements into clear observations for adult coaches and authorized project partners.
• Develop video overlays, reports, presentations, dashboards, and interactive applications.
• Communicate both the value and limitations of each analysis.
• Gather feedback from coaches and translate recurring needs into organized software and research priorities.

4. Expand Interdisciplinary Education and Research

• Bring together students from engineering, exercise science, computer science, data science, biomechanics, communication, and related disciplines.
• Give students experience working with researchers, software developers, healthcare collaborators, and community partners.
• Develop student capabilities in technical analysis, project management, communication, and responsible AI use.
• Create pathways from academic research credit to advanced research projects and potential paid laboratory positions.

5. Build a Sustainable Research and Outreach Platform

• Continue development of the Data-Driven Engineering in Athletics initiative from 2024 through 2030.
• Support research publications, conference presentations, educational demonstrations, and community partnerships.
• Expand the number of sports, movements, and research questions that can be studied.
• Develop tools and workflows that can be used responsibly at scale while protecting athlete privacy.

Research Progress

Fall 2026 Research Credit Experience

The Fall Semester opportunity is an interdisciplinary research and outreach experience involving sports biomechanics, exercise science, engineering, artificial intelligence, video analysis, and community engagement.

Students complete 126 documented hours, averaging approximately nine hours per week for 14 weeks. The experience may be completed for CBE 498R or EXSC 399R credit with advance approval from the appropriate department.

Semester Requirement	126 documented hours
Typical Weekly Commitment	Approximately 9 hours
Team Meetings	Tuesdays and Thursdays at 10:00 a.m. in CB 396
Credit Options	CBE 498R or EXSC 399R, subject to departmental approval
Primary Activities	Video processing, analysis review, reporting, application testing, documentation, and outreach coordination
Potential Next Step	Consideration for a paid student position after successful completion

Specific Research Credit Objectives

By the end of the semester, students should be able to accomplish the following objectives.

1. Apply AI and Computer Vision to Sports Biomechanics

• Explain how pose estimation, computer vision, and artificial intelligence are used to analyze human movement.
• Prepare authorized videos for quantitative movement analysis.
• Use approved applications to process running, basketball, or other athletic movement videos.
• Connect AI-generated measurements with relevant anatomy, biomechanics, and performance concepts.

2. Evaluate Video and Data Quality

• Assess camera position, frame rate, athlete visibility, completeness, and compatibility with the analysis tools.
• Recognize when video quality is insufficient for reliable analysis.
• Organize videos using approved athlete identifiers and structured naming conventions.
• Maintain accurate intake, processing, quality-control, and delivery records.

3. Review AI-Generated Results

• Evaluate measurements for technical and biomechanical plausibility.
• Identify possible errors, uncertainty, limitations, or inconsistent outputs.
• Compare automated results with the original video and available contextual information.
• Document analyses that require additional footage, human review, or technical improvement.

4. Communicate Technical Findings

• Prepare video overlays, analysis summaries, coaching reports, and presentations.
• Translate technical results into clear observations for adult coaches and authorized project partners.
• Explain the capabilities and limitations of the analysis without overstating conclusions.
• Support progress presentations and a final stakeholder presentation.

5. Contribute to Research and Software Development

• Participate in application testing and quality assurance.
• Document bugs, workflow challenges, and data-quality concerns.
• Translate coach and partner feedback into organized feature requests.
• Contribute to research questions, technical documentation, datasets, application improvements, or validation studies appropriate to the student's background.

6. Demonstrate Professional Project Execution

• Attend required Tuesday and Thursday team meetings.
• Submit an accurate timesheet each Friday.
• Complete assigned action items before the following Tuesday meeting.
• Communicate reliably with faculty, project leaders, software developers, Application Engineers, and project partners.

Qualifications

Required

• Current BYU student eligible to enroll in CBE 498R or EXSC 399R, subject to departmental approval.
• Availability for Tuesday and Thursday meetings at 10:00 a.m. in CB 396.
• Ability to complete 126 documented hours during Fall Semester.
• Strong organization, reliability, written communication, and attention to detail.
• Willingness to learn video-processing, AI-analysis, and data-management tools.
• Ability to protect confidential athlete information and follow approved procedures.

Helpful Background

Students from a range of majors and experience levels are encouraged to apply. Helpful areas include:

• Exercise science, biomechanics, or kinesiology
• Chemical, mechanical, electrical, or computer engineering
• Data science, statistics, computer science, or artificial intelligence
• Computer vision or pose estimation
• Running, track and field, basketball, coaching, or sports performance
• Video editing, technical writing, presentations, or data management
• Professional outreach or collaboration with coaches and community organizations

How to Apply

1. Review the complete internship description.
2. Complete the student application included in Part II.
3. Attach a current résumé.
4. Return the completed application and résumé to john.hedengren@byu.edu.

Selected applicants may be invited to a brief interview with the project leadership team. Students who complete the experience are considered for a paid student position in the lab.

Empowering Athletes with Data Analytics

The Roadrunner High School Outreach Program demonstrates how data science and engineering can contribute to athletic performance and informed decision-making.

The program introduces students, athletes, and coaches to video analysis, biomechanics, artificial intelligence, and data visualization. It also provides authorized video and feedback pathways that support the broader Data-Driven Engineering in Athletics research initiative.

Future Progress

The Data-Driven Engineering in Athletics initiative is expected to continue through 2030. Future work includes expanding research collaborations, improving measurement methods, developing new analysis applications, presenting findings at conferences, and creating responsible tools that help coaches and researchers better understand athletic movement.

Team Lead: McGyver Clark

McGyver Clark is a data scientist and software developer specializing in machine learning, deep learning, and data-driven athletic performance analysis. He leads the Roadrunner Outreach Program, which applies innovative AI models to sports biomechanics and athletic performance.

His work includes developing web applications that help athletes and coaches better understand movement and training. Clark earned a B.S. in Economics from Brigham Young University, with experience in econometrics, machine learning, and strategic analytics. As an assistant head coach for sprints and hurdles at Timpview High School, he helped lead the team to multiple state championships and has demonstrated an ability to translate technical analysis into practical coaching applications.

Prof. Iain Hunter

Iain Hunter joined Brigham Young University in 2001 after completing a Ph.D. in Health and Human Performance at Oregon State University. His research focuses on .

USA Track and Field has used his biomechanics expertise for many years to film, measure, and advise elite track and field athletes, particularly in the steeplechase. His interest in biomechanics developed from his experience as a BYU 800-meter runner. He later shifted his focus to the marathon, becoming the oldest athlete to win the St. George Marathon and recording a personal best of 2:20:53.

Prof. John Hedengren

John Hedengren joined Brigham Young University as a professor in 2011 after working at ExxonMobil and completing a Ph.D. in Chemical Engineering at the University of Texas at Austin.

His research focuses on process control, optimization, artificial intelligence, and machine-learning applications in energy systems, advanced manufacturing, and athletics. His teaching and professional interests center on connecting academic research with practical industry and community applications.

A former NCAA All-American in cross-country, Hedengren was inducted into the BYU Athletic Hall of Fame. His background in athletics influences his work with students and collaborators to apply engineering analysis, disciplined experimentation, and data-driven methods to sports performance.

For more information about the project or research-credit opportunities, contact John Hedengren.