Lightweight UAV Detection Method Based on IASL-YOLO
The widespread application of drone technology has raised security concerns, as unauthorized drones can lead to illegal intrusions and privacy breaches. Traditional detection methods often fall short in balancing performance and lightweight design, making them unsuitable for resource-constrained sce...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/5/325 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257616515629056 |
|---|---|
| author | Huaiyu Yang Bo Liang Song Feng Ji Jiang Ao Fang Chunyun Li |
| author_facet | Huaiyu Yang Bo Liang Song Feng Ji Jiang Ao Fang Chunyun Li |
| author_sort | Huaiyu Yang |
| collection | DOAJ |
| description | The widespread application of drone technology has raised security concerns, as unauthorized drones can lead to illegal intrusions and privacy breaches. Traditional detection methods often fall short in balancing performance and lightweight design, making them unsuitable for resource-constrained scenarios. To address this, we propose the IASL-YOLO algorithm, which optimizes the YOLOv8s model to enhance detection accuracy and lightweight efficiency. First, we design the CFE-AFPN network to streamline the architecture while boosting feature fusion capabilities across non-adjacent layers. Second, we introduce the SIoU loss function to address the orientation mismatch issue between predicted and ground truth bounding boxes. Finally, we employ the LAMP pruning algorithm to compress the model. Experimental results on the Anti-UAV dataset show that the improved model achieves a 2.9% increase in Precision, a 6.8% increase in Recall, and 3.9% and 3.8% improvements in mAP50 and mAP50-95, respectively. Additionally, the model size is reduced by 75%, the parameter count by 78%, and computational workload by 30%. Compared to mainstream algorithms, IASL-YOLO demonstrates significant advantages in both performance and lightweight design, offering an efficient solution for drone detection tasks. |
| format | Article |
| id | doaj-art-e0d50984c5d5485a9afb60e048fe9118 |
| institution | OA Journals |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-e0d50984c5d5485a9afb60e048fe91182025-08-20T01:56:23ZengMDPI AGDrones2504-446X2025-04-019532510.3390/drones9050325Lightweight UAV Detection Method Based on IASL-YOLOHuaiyu Yang0Bo Liang1Song Feng2Ji Jiang3Ao Fang4Chunyun Li5Yunnan Key Laboratory of Computer Technology Application, Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaYunnan Key Laboratory of Computer Technology Application, Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaYunnan Key Laboratory of Computer Technology Application, Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaSchool of Information and Network Security, Yunnan Police College, Kunming 650223, ChinaYunnan Key Laboratory of Computer Technology Application, Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaKunming Educational Science Research Institute, Kunming 650031, ChinaThe widespread application of drone technology has raised security concerns, as unauthorized drones can lead to illegal intrusions and privacy breaches. Traditional detection methods often fall short in balancing performance and lightweight design, making them unsuitable for resource-constrained scenarios. To address this, we propose the IASL-YOLO algorithm, which optimizes the YOLOv8s model to enhance detection accuracy and lightweight efficiency. First, we design the CFE-AFPN network to streamline the architecture while boosting feature fusion capabilities across non-adjacent layers. Second, we introduce the SIoU loss function to address the orientation mismatch issue between predicted and ground truth bounding boxes. Finally, we employ the LAMP pruning algorithm to compress the model. Experimental results on the Anti-UAV dataset show that the improved model achieves a 2.9% increase in Precision, a 6.8% increase in Recall, and 3.9% and 3.8% improvements in mAP50 and mAP50-95, respectively. Additionally, the model size is reduced by 75%, the parameter count by 78%, and computational workload by 30%. Compared to mainstream algorithms, IASL-YOLO demonstrates significant advantages in both performance and lightweight design, offering an efficient solution for drone detection tasks.https://www.mdpi.com/2504-446X/9/5/325AFPNEMAFasterNetlightweightLAMPSIoU |
| spellingShingle | Huaiyu Yang Bo Liang Song Feng Ji Jiang Ao Fang Chunyun Li Lightweight UAV Detection Method Based on IASL-YOLO Drones AFPN EMA FasterNet lightweight LAMP SIoU |
| title | Lightweight UAV Detection Method Based on IASL-YOLO |
| title_full | Lightweight UAV Detection Method Based on IASL-YOLO |
| title_fullStr | Lightweight UAV Detection Method Based on IASL-YOLO |
| title_full_unstemmed | Lightweight UAV Detection Method Based on IASL-YOLO |
| title_short | Lightweight UAV Detection Method Based on IASL-YOLO |
| title_sort | lightweight uav detection method based on iasl yolo |
| topic | AFPN EMA FasterNet lightweight LAMP SIoU |
| url | https://www.mdpi.com/2504-446X/9/5/325 |
| work_keys_str_mv | AT huaiyuyang lightweightuavdetectionmethodbasedoniaslyolo AT boliang lightweightuavdetectionmethodbasedoniaslyolo AT songfeng lightweightuavdetectionmethodbasedoniaslyolo AT jijiang lightweightuavdetectionmethodbasedoniaslyolo AT aofang lightweightuavdetectionmethodbasedoniaslyolo AT chunyunli lightweightuavdetectionmethodbasedoniaslyolo |