ConductVision Sports

Give scouts consistent data on your players

During an academy pilot, ConductVision measures each player the same way every session and builds a player profile the academy can share with scouts.

Plan a pilotRead the research
A defender 5 feet from a shooter close to the hoop, drawn to scaleThe area near the basket on a college court, with the lane, the rim and part of the three-point line. A circle of radius 5 feet surrounds a shooter near the rim, and a defender stands on the circle.ShooterDefender5 ft10 ft

Even a defender 5 feet away lowered the chance that a shot close to the hoop went in. Drawn to scale on a college court.

The research

Why scouts want video data

NBA teams lack detailed tracking data on college players, because installing tracking systems in more than 300 Division I arenas is impractical.1 Tracking data pulled from college broadcast video predicted which players would reach the NBA better than play-by-play data did.1

One published method, using video from a single moving camera like those used in sports broadcasts, placed players within a foot of their true location 94.5% of the time in early tests.2

Defense

How closely each shot was guarded

In 15,835 college shots with player tracking, even a defender 5 feet away substantially lowered the chance that a shot close to the hoop went in.3 If your scrimmage video covers the full court, a pilot can also measure how closely the shooter was guarded on each shot. As with every other measure, a ConductVision engineer checks a sample by hand.

What the profile contains

Profile contents

  • Shooting mechanics and shot-to-shot consistency
  • Athletic test results and season trends
  • How closely the player was guarded on each shot, where the camera covers the full court
  • The dates, drills and camera setup behind every number

Sharing

Sharing profiles

Who decides which scouts see a profile?

The academy and the player decide. Profiles of players under 18 are shared only with a parent or guardian's permission.

Can scouts compare players from different academies?

Only when every academy uses the same measurement system, drills and camera setup. Joint-tracking methods differ in where they place the hip and knee.4 In one study, each method consistently put the hip and knee about 30 to 50 mm from where lab motion capture placed them.4 Camera settings matter too, because an error of 20 milliseconds in timing foot contact changed the measured knee angle by up to 20 degrees.5

References

  1. Patton A, Scott M, Walker N, et al. (2021). Predicting NBA Talent from Enormous Amounts of College Basketball Tracking Data. MIT Sloan Sports Analytics Conference.
  2. Johnson N (2020). Extracting Player Tracking Data from Video Using Non-Stationary Cameras and a Combination of Computer Vision Techniques. MIT Sloan Sports Analytics Conference.
  3. Tenan MS, Rezai AR (2023). Player Tracking Facilitates Valid Causal Inference: The Average Treatment Effect of Defender Proximity on Scoring. MIT Sloan Sports Analytics Conference.
  4. Needham L, Evans M, Cosker DP, et al. (2021). The accuracy of several pose estimation methods for 3D joint centre localisation. Scientific Reports.
  5. Mundt M, Colyer S, Wade L, et al. (2024). Automating Video-Based Two-Dimensional Motion Analysis in Sport? Implications for Gait Event Detection, Pose Estimation, and Performance Parameter Analysis. Scandinavian Journal of Medicine & Science in Sports.

Plan a recruiting profile pilot

Tell us about your players and the scouts you work with. A ConductVision engineer replies with a proposal.

Plan a pilotResearch and accuracy