What question did this study set out to answer?

To enhance small object detection in UAV aerial images against challenges like background interference.

December 11, 2025Applied SciencesOpen Access

Lightweight YOLO-SR: A Method for Small Object Detection in UAV Aerial Images

View Full Paper

Ask AI

Bookmark

Authors

Proposed YOLO-SR method improves small object detection accuracy in drone images, indicating efficiency gains.

To enhance small object detection in UAV aerial images against challenges like background interference.
Developed a lightweight feature extraction module.
Integrated Shuffle Attention for improved feature response.
Utilized Spatial Pyramid Pooling Attention for multi-scale contextual capture.
Applied dual-path attention mechanisms to optimize features.
Employed a decoupled detection head with dynamic loss weighting.
Achieved 5.3% improvement in precision and 13.1% in recall.
Recorded gains in mAP0.5 (11.5%) and mAP0.75 (22.3%).
Reduced parameters by 42.9% from 7.0 × 10^6 to 4.0 × 10^6.
Lowered computational cost by 37.2% from 60.0 GFLOPs to 37.7 GFLOPs.

Liang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark