PerformStars mobile app
Record, upload, and review training anywhere.
Download
Computer Vision Validation · September 3, 2026

Shot detection and outcome recognition on a complete training session

We evaluated PerformStars on a complete, unedited pool training video and compared its automatic output with a full manual review.

Manual corrections are used only as ground truth and are not counted as automatic results.

72
Real shots
65
Automatically detected
90.3%
Detection recall
Key results
90.3%

Shot Detection Recall

65 of 72 real shots were detected automatically.

95.6%

Shot Detection Precision

65 of 68 automatic shot candidates were real shots.

92.9%

F1 Score

Combined balance between detection precision and recall.

98.3%

Outcome Accuracy

57 of 58 automatic made/miss decisions were correct.

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.

72
Real shots in video
65
Automatically detected real shots
7
Missed by automatic detection
3
False automatic detections
Recall: 65 / 72 = 90.3%
Precision: 65 / 68 = 95.6%
F1: 92.9%

The seven shots found during manual review are not included in the automatic detection result.

Made / Miss Recognition

We separately evaluated whether PerformStars could correctly determine the result of shots it had already detected.

65
Automatically detected real shots
58
Automatic made/miss decisions
57
Correct decisions
1
Incorrect decisions
7
Unknown / no decision
98.3%

Accuracy when a decision was made

57 of 58 automatic made/miss decisions were correct.

89.2%

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.

57 of 65 automatically detected shots received both an automatic outcome and the correct result — 87.7%.

Methodology

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.

01

Source video

Complete unedited training session.

02

Automatic analysis

PerformStars processed the video without manual intervention.

03

Ground-truth review

All real shots and outcomes were manually verified.

04

Comparison

Original automatic results were compared with the verified session.

Open evidence

Verify the test yourself

We are publishing both the source material and the processed workout so the results can be independently reviewed.

YouTube

Watch the source video

Complete unedited training video

Watch source video
Workout data

Explore the processed workout

Open the actual PerformStars workout and review the detected shots and their results.

Open workout data

Validation summary

72
real shots
65
automatically detected
90.3%
detection recall
95.6%
detection precision
98.3%
made/miss accuracy when the system made a decision
Test date: September 3, 2026

These results describe this specific recorded training session 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.