# Object Detection on VisDrone DET 2019

Source: [Object Detection on VisDrone DET 2019](<https://www.sota2.com/research/sota/object-detection-on-visdrone-det-2019>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-15T07:08:24.198Z

Evaluation of Object Detection performance on the VisDrone DET 2019 dataset, reporting the Average Precision at IoU=0.50 (AP50).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Object Detection |
| Dataset (including any stated split) | VisDrone DET 2019 |
| Metric | AP50 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [AP50](<https://www.sota2.com/research/sota/object-detection-on-visdrone-det-2019.md?metric=AP50>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP50 | Result date | Report paper |
| --- | --- | --- | --- |
| YOLOv8-S + FINE | 47.2 | Not recorded | 6a2f8720d33dfb23e783c04c |
| YOLOv5-S + FINE | 46.9 | Not recorded | 6a2f8720d33dfb23e783c04c |
| YOLOv8-S | 46.3 | Not recorded | 6a2f8720d33dfb23e783c04c |
| YOLOv5-S | 45.9 | Not recorded | 6a2f8720d33dfb23e783c04c |
| YOLOv6-S v3.0 + FINE | 45.6 | Not recorded | 6a2f8720d33dfb23e783c04c |
| YOLOv6-S v3.0 | 44.8 | Not recorded | 6a2f8720d33dfb23e783c04c |

### YOLOv8-S + FINE

AP50: 47.2. Result ID: 6a2fa470fbc373592c2b6fa9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

Recorded evaluation configuration: {"Fusion Method":"PAN + FINE","FLOPs":"49.2G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

### YOLOv5-S + FINE

AP50: 46.9. Result ID: 6a2fa470fbc373592c2b6fa5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

Recorded evaluation configuration: {"Fusion Method":"PAN + FINE","FLOPs":"40.8G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

### YOLOv8-S

AP50: 46.3. Result ID: 6a2fa470fbc373592c2b6fa8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

Recorded evaluation configuration: {"Fusion Method":"PAN","FLOPs":"44.7G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

### YOLOv5-S

AP50: 45.9. Result ID: 6a2fa470fbc373592c2b6fa4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

Recorded evaluation configuration: {"Fusion Method":"PAN","FLOPs":"37.5G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

### YOLOv6-S v3.0 + FINE

AP50: 45.6. Result ID: 6a2fa470fbc373592c2b6fa7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

Recorded evaluation configuration: {"Fusion Method":"PAN + FINE","FLOPs":"74.5G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

### YOLOv6-S v3.0

AP50: 44.8. Result ID: 6a2fa470fbc373592c2b6fa6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f8720d33dfb23e783c04c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f445.md>)

[Implementation](<https://github.com/meituan/YOLOv6>)

Recorded evaluation configuration: {"Fusion Method":"PAN","FLOPs":"72.2G","Resolution":"800 × 800"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.