ConductVision Sports

Measure how each player shoots and moves

During a pilot at your academy, ConductVision measures each player's shooting mechanics, jumps and movement from practice video and tracks the numbers across sessions.

Plan a pilotSee the study
Better and weaker three-point shooters, from the bottom of the load to releaseAverage positions measured in 11 better and 13 weaker three-point shooters. At the bottom of the load the better shooters bend more at the knee, hip and ankle. Both groups release the ball at the same height.Better shooters, 11 playersWeaker shooters, 13 playersBottom of the loadRelease height, both groups

Better three-point shooters sink lower, then release at the same height. Averages measured in 24 players. See the study

From the science

How better three-point shooters load the shot

Average positions of better and weaker three-point shootersLeft, the bottom of the load: better shooters bend the knee 18.9 degrees, the hip 12.8 degrees and the ankle 12.2 degrees more. Right, release: both groups release the ball at about 1.20 times their height.Better shooters, 11 playersWeaker shooters, 13 playersBottom of the loadReleaseRelease height, both groups
The measured averages

Joint angles are measured inside the joint, so a smaller angle means more bend. Better shooters made at least 5 of 10 test three-pointers.

MeasureBetter (11)Weaker (13)Real difference?
Knee angle, bottom of the load94.3°113.2°Yes
Hip angle, bottom of the load143.1°155.9°Yes
Ankle angle, bottom of the load50.1°62.3°Yes
Center of mass height, bottom of the load, times body height0.490.56Yes
Release height, times body height1.201.19Within chance
Jump height at release25.8 cm23.7 cmWithin chance

When researchers filmed 24 players and tracked their joints from the video, better three-point shooters bent more at the hip, knee and ankle while loading the shot than weaker shooters.1 The better shooters were those who made at least 5 of 10 test three-pointers.1 At the bottom of the load, the knee bent 19 degrees more, the hip 13 degrees more and the ankle 12 degrees more.1 Both groups then released the ball at about 1.2 times their own height.1

Compare the knees at the bottom of the load, where a smaller joint angle means more bend. Each figure is one group's average joint angles on a body of standard proportions, so it shows posture rather than any one player.

What you get

What a pilot measures for each player

  • Shooting mechanics

    Release height, release speed, trunk lean and knee bend on every shot, and how much each varies from shot to shot. Among 12 players, the less the ball's speed at release varied from shot to shot, the more accurate the shooter was from three-point range.2

    Shooting mechanics

  • Shooting progress

    Each shot's flight and the shooter's motion, tracked alongside makes and misses. In NBA data, chance explained more than half of the differences between players' three-point percentages over a season.3 Makes and misses alone can mislead.

    Shooting progress

  • Athletic profile

    Jump height, takeoff and landing mechanics, sprint times and change-of-direction times, measured the same way at every test. At the NBA Draft Combine, drafted players jumped higher and ran faster than undrafted players.4

    Athletic profile

  • Recruiting profiles

    A player profile, measured the same way every session, that the academy can share with college and professional scouts. Even NBA teams lack detailed tracking data on college players.5

    Recruiting profiles

The research

What a shot's flight and a player's motion add to shooting percentage

In an analysis of over 22 million shots, shooting percentage ranked shooters reliably only after more than 1,000 shots per shooter.6 In the same analysis, a rating built from the ball's flight estimated shooting skill more accurately after a 25-shot session than that session's shooting percentage.6

In about 1,500 NBA three-pointers filmed on broadcast video, made and missed shots differed in body position and movement, whether open or contested.7

With a pilot, coaches see how each shot was taken as well as whether it went in.

How a pilot works

From practice video to player profiles

  1. 1

    Film the agreed drills

    A ConductVision engineer sends a proposal with the drills, camera positions and frame rates. Staff then film shooting drills, jump tests and scrimmages from the side and the front.

  2. 2

    ConductVision measures each player

    ConductVision tracks each player's joints and the ball in the video and calculates each measure in the proposal.

  3. 3

    Review each profile

    Coaches receive a profile for each player, a trend across sessions and a check of ConductVision's accuracy on their own video. Academies with an analyst also receive every measure as a data file.

  4. 4

    Decide whether to continue

    The pilot ends with a results review and a decision about adding more players or teams.

Accuracy

Is video accurate enough to see these gaps?

Markerless systems track joints from video, without the body markers that lab motion capture uses. Across 20 studies of jumps, markerless knee angles differed from lab motion capture by 4.4 degrees, hip angles by 5.3 degrees and ankle angles by 4.9 degrees (root-mean-square error).8 In the chart, each gap between better and weaker shooters is two to four times the error at that joint.1,8

In a study that filmed two athletes together, wrist angles were the only joint angles without acceptable agreement with lab motion capture, one reason a pilot films one player at a time.9

These studies tested other markerless systems. Each pilot checks ConductVision's accuracy on your own video. A ConductVision engineer measures sample frames by hand, and the pilot reports how closely ConductVision agrees before anyone relies on a profile.

Research and accuracy
Gaps between better and weaker shooters against the error of markerless video, in degreesGap between better and weaker shootersMarkerless video error, root-mean-square with 95% CI0°5°10°15°20°KneeKnee: 18.9° gap between groups18.9°Knee: error 4.4° (95% CI 2.9° to 5.9°)4.4°HipHip: 12.8° gap between groups12.8°Hip: error 5.3° (95% CI 2.9° to 7.6°)5.3°AnkleAnkle: 12.2° gap between groups12.2°Ankle: error 4.9° (95% CI 3.9° to 5.9°)4.9°

Questions

Questions from academies

What equipment do we need?

Two cameras per drill, one at the side and one in front. For shooting and jump measures, film one player at a time. Measures of the ball at the rim need a camera that also sees the rim. Phones can serve as the cameras if they record at the frame rates in the proposal. Jump and sprint tests need 100 frames per second or more, the rate one study found necessary to detect when a foot touches down.10 In published studies, timing apps using high-speed iPhone video matched a force plate and timing gates almost perfectly for jump height and sprint times.11,12 Scrimmage video that covers the full court adds how closely each player was guarded on each shot.

How are the length and price of a pilot set?

The proposal sets the length, the number of players, how you send video, how soon profiles come back and the price for your academy.

Does ConductVision tell us what to coach?

No. The profile reports measurements, and your coaches decide what to change.

Who owns the video and the data?

The academy keeps ownership of its video and data. Each pilot starts with a written plan for storage, access and deletion.

Can we film players under 18?

Yes, with consent. The academy collects written consent from a parent or guardian before filming any player under 18. Profiles of players under 18 go to scouts only with the family's permission.

Is this a medical or injury assessment?

No. The measurements describe movement only.

References

  1. Cabarkapa D, Cabarkapa DV, Fry AC (2026). Biomechanical determinants of proficient 3-point shooters: markerless motion capture analysis. Frontiers in Sports and Active Living.
  2. Slegers N, Lee D, Wong G (2021). The Relationship of Intra-Individual Release Variability with Distance and Shooting Performance in Basketball. Journal of Sports Science & Medicine.
  3. Franks AM, D’Amour A, Cervone D, et al. (2016). Meta-analytics: tools for understanding the statistical properties of sports metrics. Journal of Quantitative Analysis in Sports.
  4. Cui Y, Liu F, Bao D, et al. (2019). Key Anthropometric and Physical Determinants for Different Playing Positions During National Basketball Association Draft Combine Test. Frontiers in Psychology.
  5. 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.
  6. Marty R (2018). High-resolution shot capture reveals systematic biases and an improved method for shooter evaluation. MIT Sloan Sports Analytics Conference.
  7. Panna F, Lucey P (2017). “Body Shots”: Analyzing Shooting Styles in the NBA using Body-Pose Attributes. MIT Sloan Sports Analytics Conference.
  8. Ogura A, Florio E, Wileman TM, et al. (2026). Are we there yet? A systematic review and meta-analysis of the validity and reliability of automated markerless motion capture systems during jumping tasks. Journal of Sports Sciences.
  9. Oonk GA, Kempe M, Lemmink KAPM, et al. (2026). Examining the concurrent validity of markerless motion capture in dual-athlete team sports movements. Journal of Sports Sciences.
  10. 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.
  11. Balsalobre-Fernández C, Glaister M, Lockey RA (2015). The validity and reliability of an iPhone app for measuring vertical jump performance. Journal of Sports Sciences.
  12. Romero-Franco N, Jiménez-Reyes P, Castaño-Zambudio A, et al. (2017). Sprint performance and mechanical outputs computed with an iPhone app: Comparison with existing reference methods. European Journal of Sport Science.

Plan an academy pilot

Tell us about your players, the video you record and the first question you want answered. A ConductVision engineer replies with a proposal.

Plan a pilotResearch and accuracy