A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8
Aiming at the characteristics of remote sensing images such as a complex background, a large number of small targets, and various target scales, this paper presents a remote sensing image target detection algorithm based on improved YOLOv8. First, in order to extract more information about small tar...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/4/1557 |
| _version_ | 1797299059621363712 |
|---|---|
| author | Haoyu Wang Haitao Yang Hang Chen Jinyu Wang Xixuan Zhou Yifan Xu |
| author_facet | Haoyu Wang Haitao Yang Hang Chen Jinyu Wang Xixuan Zhou Yifan Xu |
| author_sort | Haoyu Wang |
| collection | DOAJ |
| description | Aiming at the characteristics of remote sensing images such as a complex background, a large number of small targets, and various target scales, this paper presents a remote sensing image target detection algorithm based on improved YOLOv8. First, in order to extract more information about small targets in images, we add an extra detection layer for small targets in the backbone network; second, we propose a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance the network’s ability to detect targets of different sizes; and lastly, Wise-IoU is used to replace the CIoU loss function in the original algorithm to improve the robustness of the model. Using our improved algorithm for the detection of multiple target categories in the DOTAv1.0 dataset, the mAP@0.5 value is 82.7%, which is 1.3% higher than that of the original YOLOv8 algorithm. It is proven that the algorithm proposed in this paper can effectively improve target detection accuracy in remote sensing images. |
| first_indexed | 2024-03-07T22:44:03Z |
| format | Article |
| id | doaj.art-e82ee2afa57a4fa7849e2d2a12f3f45d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-07T22:44:03Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e82ee2afa57a4fa7849e2d2a12f3f45d2024-02-23T15:06:23ZengMDPI AGApplied Sciences2076-34172024-02-01144155710.3390/app14041557A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8Haoyu Wang0Haitao Yang1Hang Chen2Jinyu Wang3Xixuan Zhou4Yifan Xu5Graduate School, Space Engineering University, Beijing 101416, ChinaSpace Engineering University, Beijing 101416, ChinaSpace Engineering University, Beijing 101416, ChinaGraduate School, Space Engineering University, Beijing 101416, ChinaGraduate School, Space Engineering University, Beijing 101416, ChinaGraduate School, Space Engineering University, Beijing 101416, ChinaAiming at the characteristics of remote sensing images such as a complex background, a large number of small targets, and various target scales, this paper presents a remote sensing image target detection algorithm based on improved YOLOv8. First, in order to extract more information about small targets in images, we add an extra detection layer for small targets in the backbone network; second, we propose a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance the network’s ability to detect targets of different sizes; and lastly, Wise-IoU is used to replace the CIoU loss function in the original algorithm to improve the robustness of the model. Using our improved algorithm for the detection of multiple target categories in the DOTAv1.0 dataset, the mAP@0.5 value is 82.7%, which is 1.3% higher than that of the original YOLOv8 algorithm. It is proven that the algorithm proposed in this paper can effectively improve target detection accuracy in remote sensing images.https://www.mdpi.com/2076-3417/14/4/1557remote sensing imagetarget detectionYOLOv8EMAWise-IoU |
| spellingShingle | Haoyu Wang Haitao Yang Hang Chen Jinyu Wang Xixuan Zhou Yifan Xu A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 Applied Sciences remote sensing image target detection YOLOv8 EMA Wise-IoU |
| title | A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 |
| title_full | A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 |
| title_fullStr | A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 |
| title_full_unstemmed | A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 |
| title_short | A Remote Sensing Image Target Detection Algorithm Based on Improved YOLOv8 |
| title_sort | remote sensing image target detection algorithm based on improved yolov8 |
| topic | remote sensing image target detection YOLOv8 EMA Wise-IoU |
| url | https://www.mdpi.com/2076-3417/14/4/1557 |
| work_keys_str_mv | AT haoyuwang aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT haitaoyang aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT hangchen aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT jinyuwang aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT xixuanzhou aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT yifanxu aremotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT haoyuwang remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT haitaoyang remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT hangchen remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT jinyuwang remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT xixuanzhou remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 AT yifanxu remotesensingimagetargetdetectionalgorithmbasedonimprovedyolov8 |