PS-YOLO: A Lighter and Faster Network for UAV Object Detection
The operational environment of UAVs poses unique challenges for object detection compared to conventional methods. When UAVs capture remote sensing images from elevated altitudes, objects often appear minuscule and can be easily obscured by complex backgrounds. This increases the likelihood of false...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/9/1641 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030249330343936 |
|---|---|
| author | Han Zhong Yan Zhang Zhiguang Shi Yu Zhang Liang Zhao |
| author_facet | Han Zhong Yan Zhang Zhiguang Shi Yu Zhang Liang Zhao |
| author_sort | Han Zhong |
| collection | DOAJ |
| description | The operational environment of UAVs poses unique challenges for object detection compared to conventional methods. When UAVs capture remote sensing images from elevated altitudes, objects often appear minuscule and can be easily obscured by complex backgrounds. This increases the likelihood of false positives and missed detections, thereby complicating the detection process. Furthermore, the hardware resources available on UAV platforms are typically highly constrained. To meet deployment requirements, researchers often must compromise some detection accuracy in favor of a more lightweight model. To address these challenges, we propose PS-YOLO, a fast and precise network specifically designed for UAV-based object detection. In the proposed network, we first design a lightweight backbone based on partial convolution. Then, we introduce a more efficient neck network called FasterBIFFPN to replace the original PAFPN, enabling more effective multi-scale feature fusion. Finally, we propose the GSCD head. GSCD employs shared convolutions to enhance the network’s ability to learn common features across objects of different scales and introduces Normalized Gaussian Wasserstein Distance Loss (NWDLoss) to improve detection accuracy. This detection head effectively increases inference speed without significantly increasing parameter counts. The proposed PS-YOLO is validated on the Visdrone2019 dataset, and the results demonstrate that PS-YOLO provides a 2% improvement in precision, 0.5% improvement in recall, 1.3% improvement in mean average precision (mAP), 41.3% reduction in parameter counts, 6.1% reduction in computational cost, and 26.73 FPS improvement in inference speed compared to the benchmark model YOLOv11-s. |
| format | Article |
| id | doaj-art-3aef572b494b4e719ec6f8e220ffeeb4 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-3aef572b494b4e719ec6f8e220ffeeb42025-08-20T02:59:15ZengMDPI AGRemote Sensing2072-42922025-05-01179164110.3390/rs17091641PS-YOLO: A Lighter and Faster Network for UAV Object DetectionHan Zhong0Yan Zhang1Zhiguang Shi2Yu Zhang3Liang Zhao4College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThe operational environment of UAVs poses unique challenges for object detection compared to conventional methods. When UAVs capture remote sensing images from elevated altitudes, objects often appear minuscule and can be easily obscured by complex backgrounds. This increases the likelihood of false positives and missed detections, thereby complicating the detection process. Furthermore, the hardware resources available on UAV platforms are typically highly constrained. To meet deployment requirements, researchers often must compromise some detection accuracy in favor of a more lightweight model. To address these challenges, we propose PS-YOLO, a fast and precise network specifically designed for UAV-based object detection. In the proposed network, we first design a lightweight backbone based on partial convolution. Then, we introduce a more efficient neck network called FasterBIFFPN to replace the original PAFPN, enabling more effective multi-scale feature fusion. Finally, we propose the GSCD head. GSCD employs shared convolutions to enhance the network’s ability to learn common features across objects of different scales and introduces Normalized Gaussian Wasserstein Distance Loss (NWDLoss) to improve detection accuracy. This detection head effectively increases inference speed without significantly increasing parameter counts. The proposed PS-YOLO is validated on the Visdrone2019 dataset, and the results demonstrate that PS-YOLO provides a 2% improvement in precision, 0.5% improvement in recall, 1.3% improvement in mean average precision (mAP), 41.3% reduction in parameter counts, 6.1% reduction in computational cost, and 26.73 FPS improvement in inference speed compared to the benchmark model YOLOv11-s.https://www.mdpi.com/2072-4292/17/9/1641UAVremote sensingobject detectionlightweight networkpartial convolutionshared convolution |
| spellingShingle | Han Zhong Yan Zhang Zhiguang Shi Yu Zhang Liang Zhao PS-YOLO: A Lighter and Faster Network for UAV Object Detection Remote Sensing UAV remote sensing object detection lightweight network partial convolution shared convolution |
| title | PS-YOLO: A Lighter and Faster Network for UAV Object Detection |
| title_full | PS-YOLO: A Lighter and Faster Network for UAV Object Detection |
| title_fullStr | PS-YOLO: A Lighter and Faster Network for UAV Object Detection |
| title_full_unstemmed | PS-YOLO: A Lighter and Faster Network for UAV Object Detection |
| title_short | PS-YOLO: A Lighter and Faster Network for UAV Object Detection |
| title_sort | ps yolo a lighter and faster network for uav object detection |
| topic | UAV remote sensing object detection lightweight network partial convolution shared convolution |
| url | https://www.mdpi.com/2072-4292/17/9/1641 |
| work_keys_str_mv | AT hanzhong psyoloalighterandfasternetworkforuavobjectdetection AT yanzhang psyoloalighterandfasternetworkforuavobjectdetection AT zhiguangshi psyoloalighterandfasternetworkforuavobjectdetection AT yuzhang psyoloalighterandfasternetworkforuavobjectdetection AT liangzhao psyoloalighterandfasternetworkforuavobjectdetection |