A collection of images for detecting drones across multiple environmental conditions. The dataset is prepared for the YOLOv8 object detection framework and includes five classes of drone types. It was sourced from Kaggle, but the author, organization, and specific creation date are unknown.
Use Cases
- Train a YOLOv8 object detection model based on the five drone type classes.
- Benchmark model robustness based on the day, night, and hazy environmental conditions.
- Fine-tune a pre-trained detector for specific drone types based on the labeled classes.
Strengths
- Includes images captured in three distinct environmental conditions: day, night, and hazy.
- Contains annotations for five different classes of drone types.
Limitations
- Row count and dataset size are unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
- Description metadata is limited; actual data quality requires manual inspection after download.