From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution
This work solves the problem of detecting small, clustered objects in aerial images for applications like surveillance or mapping, representing an incremental improvement over existing methods.
The paper tackles the problem of aerial object detection by addressing small object sizes and image quality degradation, achieving a 52.5% mAP on VisDrone with 27.7M parameters and a total improvement of +5.5% mAP over baseline YOLOv5.
Aerial object detection presents challenges from small object sizes, high density clustering, and image quality degradation from distance and motion blur. These factors create an information bottleneck where limited pixel representation cannot encode sufficient discriminative features. B2BDet addresses this with a two-stage framework that applies domain-specific super-resolution during inference, followed by detection using an enhanced YOLOv5 architecture. Unlike training-time super-resolution approaches that enhance learned representations, our method recovers visual information from each input image. The approach combines aerial-optimized SRGAN fine-tuning with architectural innovations including an Efficient Attention Module (EAM) and Cross-Layer Feature Pyramid Network (CLFPN). Evaluation across four aerial datasets shows performance gains, with VisDrone achieving 52.5% mAP using only 27.7M parameters. Ablation studies show that super-resolution preprocessing contributes +2.6% mAP improvement while architectural enhancements add +2.9%, yielding +5.5% total improvement over baseline YOLOv5. The method achieves computational efficiency with 53.8% parameter reduction compared to recent approaches while achieving strong small object detection performance.