SR-YOLO: Spatial-to-Depth Enhanced Multi-Scale Attention Network for Small Target Detection in UAV Aerial Imagery
Open Access
- 14 July 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (14) , 2441
Abstract
The detection of aerial imagery captured by Unmanned Aerial Vehicles (UAVs) is widely employed across various domains, including engineering construction, traffic regulation, and precision agriculture. However, aerial images are typically characterized by numerous small targets, significant occlusion issues, and densely clustered targets, rendering traditional detection algorithms largely ineffective for such imagery. This work proposes a small target detection algorithm, SR-YOLO. It is specifically tailored to address these challenges in UAV-captured aerial images. First, the Space-to-Depth layer and Receptive Field Attention Convolution are combined, and the SR-Conv module is designed to replace the Conv module within the original backbone network. This hybrid module extracts more fine-grained information about small target features by converting image spatial information into depth information and the attention of the network to targets of different scales. Second, a small target detection layer and a bidirectional feature pyramid network mechanism are introduced to enhance the neck network, thereby strengthening the feature extraction and fusion capabilities for small targets. Finally, the model’s detection performance for small targets is improved by utilizing the Normalized Wasserstein Distance loss function to optimize the Complete Intersection over Union loss function. Empirical results demonstrate that the SR-YOLO algorithm significantly enhances the precision of small target detection in UAV aerial images. Ablation experiments and comparative experiments are conducted on the VisDrone2019 and RSOD datasets. Compared to the baseline algorithm YOLOv8s, our SR-YOLO algorithm has improved mAP@0.5 by 6.3% and 3.5% and mAP@0.5:0.95 by 3.8% and 2.3% on the datasets VisDrone2019 and RSOD, respectively. It also achieves superior detection results compared to other mainstream target detection methods.Keywords
Funding Information
- National Natural Science Foundation (NNSF) of China (62471241)
This publication has 34 references indexed in Scilit:
- Underwater Image Captioning With AquaSketch-Enhanced Cross-Scale Information FusionIEEE Transactions on Geoscience and Remote Sensing, 2025
- Underwater image captioning via attention mechanism based fusion of visual and textual informationInformation Fusion, 2025
- Underwater image captioning: Challenges, models, and datasetsISPRS Journal of Photogrammetry and Remote Sensing, 2025
- LWUAVDet: A Lightweight UAV Object Detection Network on Edge DevicesIEEE Internet of Things Journal, 2024
- MFFSODNet: Multiscale Feature Fusion Small Object Detection Network for UAV Aerial ImagesIEEE Transactions on Instrumentation and Measurement, 2024
- UAV Target Detection Algorithm Based on Improved YOLOv8IEEE Access, 2023
- Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural NetworksIEEE Transactions on Geoscience and Remote Sensing, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Region-Based Convolutional Networks for Accurate Object Detection and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015