RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO
With the continuous development of deep learning technology, object detection has received extensive attention across various computer fields as a fundamental task of computational vision. Effective detection of objects in remote sensing images is a key challenge, owing to their small size and low r...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6414 |
| _version_ | 1797587540049395712 |
|---|---|
| author | Zhuang Li Jianhui Yuan Guixiang Li Hao Wang Xingcan Li Dan Li Xinhua Wang |
| author_facet | Zhuang Li Jianhui Yuan Guixiang Li Hao Wang Xingcan Li Dan Li Xinhua Wang |
| author_sort | Zhuang Li |
| collection | DOAJ |
| description | With the continuous development of deep learning technology, object detection has received extensive attention across various computer fields as a fundamental task of computational vision. Effective detection of objects in remote sensing images is a key challenge, owing to their small size and low resolution. In this study, a remote sensing image detection (RSI-YOLO) approach based on the YOLOv5 target detection algorithm is proposed, which has been proven to be one of the most representative and effective algorithms for this task. The channel attention and spatial attention mechanisms are used to strengthen the features fused by the neural network. The multi-scale feature fusion structure of the original network based on a PANet structure is improved to a weighted bidirectional feature pyramid structure to achieve more efficient and richer feature fusion. In addition, a small object detection layer is added, and the loss function is modified to optimise the network model. The experimental results from four remote sensing image datasets, such as DOTA and NWPU-VHR 10, indicate that RSI-YOLO outperforms the original YOLO in terms of detection performance. The proposed RSI-YOLO algorithm demonstrated superior detection performance compared to other classical object detection algorithms, thus validating the effectiveness of the improvements introduced into the YOLOv5 algorithm. |
| first_indexed | 2024-03-11T00:40:19Z |
| format | Article |
| id | doaj.art-af7cc2b1e59b4d0b9d0cf895e81cae10 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:40:19Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-af7cc2b1e59b4d0b9d0cf895e81cae102023-11-18T21:17:23ZengMDPI AGSensors1424-82202023-07-012314641410.3390/s23146414RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLOZhuang Li0Jianhui Yuan1Guixiang Li2Hao Wang3Xingcan Li4Dan Li5Xinhua Wang6School of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Energy and Power Engineering, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaWith the continuous development of deep learning technology, object detection has received extensive attention across various computer fields as a fundamental task of computational vision. Effective detection of objects in remote sensing images is a key challenge, owing to their small size and low resolution. In this study, a remote sensing image detection (RSI-YOLO) approach based on the YOLOv5 target detection algorithm is proposed, which has been proven to be one of the most representative and effective algorithms for this task. The channel attention and spatial attention mechanisms are used to strengthen the features fused by the neural network. The multi-scale feature fusion structure of the original network based on a PANet structure is improved to a weighted bidirectional feature pyramid structure to achieve more efficient and richer feature fusion. In addition, a small object detection layer is added, and the loss function is modified to optimise the network model. The experimental results from four remote sensing image datasets, such as DOTA and NWPU-VHR 10, indicate that RSI-YOLO outperforms the original YOLO in terms of detection performance. The proposed RSI-YOLO algorithm demonstrated superior detection performance compared to other classical object detection algorithms, thus validating the effectiveness of the improvements introduced into the YOLOv5 algorithm.https://www.mdpi.com/1424-8220/23/14/6414deep learningobject detectionYOLOremote sensing images |
| spellingShingle | Zhuang Li Jianhui Yuan Guixiang Li Hao Wang Xingcan Li Dan Li Xinhua Wang RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO Sensors deep learning object detection YOLO remote sensing images |
| title | RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO |
| title_full | RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO |
| title_fullStr | RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO |
| title_full_unstemmed | RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO |
| title_short | RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO |
| title_sort | rsi yolo object detection method for remote sensing images based on improved yolo |
| topic | deep learning object detection YOLO remote sensing images |
| url | https://www.mdpi.com/1424-8220/23/14/6414 |
| work_keys_str_mv | AT zhuangli rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT jianhuiyuan rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT guixiangli rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT haowang rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT xingcanli rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT danli rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo AT xinhuawang rsiyoloobjectdetectionmethodforremotesensingimagesbasedonimprovedyolo |