VIDEO ANALYSIS
Fruit Counter
Tests
Find missed fruit, repeated counts and unstable tracks. Change one setting at a time on the same video.
How to choose a useful test
Start with a short, representative clip containing small fruit, clusters and leaves hiding fruit. Use the same clip and manual count across comparisons. Confirm improvements on a second clip before adopting a setting.
- Missed small fruit: resolution, then confidence.
- Overlapping fruit: NMS overlap; review duplicate boxes.
- IDs changing after camera motion or occlusion: tracker and lost-track buffer.
- Brief detections inflating counts: observations before counting.
More detections do not necessarily mean better accuracy. Review each counted ID against a distinct real fruit. Duplicate IDs for one fruit are false positives. Precision, recall and F1 here evaluate unique-fruit counts after tracking; they are not frame-level mAP. Short tracks are a diagnostic, not proof of an error.
If all settings miss the same fruit, use Extract training frames on the Analysis page to build labeled training and validation data, including difficult lighting and small or occluded fruit. Keep validation videos separate from training.
Detection comparisons
Loading comparison settings…
Detection preview
Preview updates during processing, approximately every 1–2 seconds. ETA covers the remaining frames in this attempt; final encoding and later attempts take additional time.
Attempts
Each attempt retains its settings, annotated video and manual review.