Shot detection and outcome recognition on complete training sessions
We evaluated PerformStars on complete, unedited pool training videos and compared its automatic output with full manual reviews.
Manual corrections are used only as ground truth and are not counted as automatic results.
Latest test · September 14, 2026
124 real shots. A new measured session.
Shot Detection Recall
Share of real shots detected automatically in a session containing 124 real shots.
Made / Miss Accuracy
Accuracy when an automatic made/miss decision was made.
Decision Coverage
Share of automatically detected real shots receiving a made/miss decision.
This update improves motion recovery when a fast ball briefly disappears and links cue-ball movement to object-ball contact, including shots played off a cushion. Shot power and spin analysis now compares plausible motion scenarios while accounting for real table conditions.
These sessions use different source videos. Their results are individual measurements, not a controlled before-and-after comparison. Detection precision and F1 were not reported for the September 14 test.
Watch September 14 source video ↗Shot Detection Recall
65 of 72 real shots were detected automatically.
Shot Detection Precision
65 of 68 automatic shot candidates were real shots.
F1 Score
Combined balance between detection precision and recall.
Outcome Accuracy
57 of 58 automatic made/miss decisions were correct.
September 3, 2026
Automatic Shot Detection
The complete session contained 72 real shots according to the final manual review. PerformStars automatically generated 68 shot candidates. Of these, 65 were confirmed as real shots and 3 were false detections.
The seven shots found during manual review are not included in the automatic detection result.
September 3, 2026
Made / Miss Recognition
We separately evaluated whether PerformStars could correctly determine the result of shots it had already detected.
Accuracy when a decision was made
57 of 58 automatic made/miss decisions were correct.
Decision coverage
The system produced a made/miss decision for 58 of 65 automatically detected real shots.
PerformStars currently uses a conservative decision strategy. When the available signals are not strong enough, the system can return an unknown result instead of forcing a made/miss classification.
Methodology
For each test, a complete training video was processed by PerformStars using the normal automatic analysis pipeline. The session was then reviewed manually to establish ground truth for every real shot and its final result.
Automatic detections and the original automatic made/miss decisions were compared with this manual reference. Shots recovered only during manual review were not counted as automatic detections, and no manual result was substituted for an automatic result.
Source video
Complete unedited training session.
Automatic analysis
PerformStars processed the video without manual intervention.
Ground-truth review
All real shots and outcomes were manually verified.
Comparison
Original automatic results were compared with the verified session.
Verify the test yourself
Review the source video for each test. The September 3 processed workout is also available for independent review.
Watch the latest source video
Complete unedited training video. Processed workout link is not yet published.
Watch source videoExplore the processed workout
Open the actual PerformStars workout and review the detected shots and their results.
Open workout dataValidation summary
September 14, 2026 · 124 real shots
September 3, 2026 · 72 real shots
These results describe the specific recorded training sessions and should not be interpreted as a universal accuracy guarantee for every video, table, camera angle, lighting condition, or style of play.
Test PerformStars on your own session
Upload a practice video and see how PerformStars turns real footage into structured shot data and coaching analysis.