Upload a processing-line video
The video is decoded, each carcass is detected and tracked down the line, and every bird gets one grade against the Appendix 001 standard.
Queued…
AI bird counting — live demonstration reels
Two clips of the detector running: birds counted in the house, and dressed birds graded on the shackle line. Model output rendered frame by frame, with the measured numbers beside them.
How it works
Graded against the Appendix 001 Dress Bird Quality Standard (A / B / C / Reject).
Recent inspections
- WhatsApp Video 2026-07-24 at 21.34.16 (1).mp4 · 16 birds
- WhatsApp Video 2026-07-24 at 21.34.16.mp4 · 21 birds
- WhatsApp Video 2026-07-24 at 17.06.34 (1).mp4 · 51 birds
- WhatsApp Video 2026-07-24 at 17.06.34.mp4 · 46 birds
- WhatsApp Video 2026-07-24 at 17.06.35.mp4 · 52 birds
Diagnostics (internal)
Grading model
Trained on Appendix 001 reference photos plus in-domain shackle-line crops (mostly clean Grade-A birds auto-labelled and pending human confirmation). Headline accuracy is inflated by those easy normals; the hard defect classes remain weak and rare classes (broken, ammonia, reject) have almost no examples. Advisory only -- review every bird.
Measured recall per grade
| Grade | A | B | C | REJECT |
|---|---|---|---|---|
| recall | 87% | 32% | 63% | 75% |
Measured recall per defect
| Torn skin | Scratch skin | Haematoma / bruises | Broken (patah) | Broken bruises (patah lebam) | Ammonia burn | Others | Reject condition |
|---|---|---|---|---|---|---|---|
| 14% | 0% | 50% | 0% | 0% | 0% | 0% | 25% |
Data readiness (labelled examples per grade × defect)
| Torn skin | Scratch skin | Haematoma / bruises | Broken (patah) | Broken bruises (patah lebam) | Ammonia burn | Others | Reject condition | |
|---|---|---|---|---|---|---|---|---|
| A | 5 | 5 | 15 | 2 | 0 | 1 | 0 | 0 |
| B | 13 | 6 | 17 | 0 | 4 | 1 | 0 | 0 |
| C | 10 | 6 | 10 | 0 | 10 | 5 | 5 | 0 |
| REJECT | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 |