YOLOv5s_2E: Improved YOLOv5s for Aerial Small Target Detection
Open Access
- 1 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 80479-80490
Abstract
To address the issues of low accuracy in existing small object detection algorithms, an improved network model algorithm called YOLOv5s_2E is proposed. This method first uses the k-means++ clustering algorithm to calculate the prior boxes of the Visdrone dataset. Then, it introduces Soft_NMS and combines it with EIoU to propose the EIoU_Soft_NMS algorithm to replace the non-maximum suppression (NMS) of the original network, improving the detection of objects that are occluded. The bounding box regression loss function uses Focal-EIoU, which speeds up model convergence and reduces loss. Additionally, a detection layer is added to the original detection head to unify the channel numbers, and with the dynamic head framework DyHead, the attention mechanism is integrated with the detector’s head to further improve small object detection accuracy. Finally, the system robustness is improved by adjusting the ratio of data augmentation methods Mixup and Mosaic.Experimental results show that the proposed algorithm improves the mAP@0.5, mAP@0.5:0.95 and detection accuracy by 12.6%, 12.2%, and 20.5%, respectively, compared to the previous method on the VisDrone dataset. The parameter size only increases by 4%, and the weight file size increases by only 0.57MB, meeting the accuracy requirements for small object detection.Keywords
Funding Information
- National Natural Science Foundation of China (62103298)
- Natural Science Foundation of Hebei Province (F2018209289)
This publication has 27 references indexed in Scilit:
- YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers2018
- Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning MethodsContrast Media & Molecular Imaging, 2018
- A Driver’s License Test for Driverless VehiclesMechanical Engineering, 2017
- Deformable Convolutional Networks2017
- Soft-NMS — Improving Object Detection with One Line of Code2017
- Mask R-CNN2017
- UnitBox2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fast R-CNN2015