RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images
Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic de...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/17/8707 |
| _version_ | 1797496293542592512 |
|---|---|
| author | Lei Yang Guowu Yuan Hao Zhou Hongyu Liu Jian Chen Hao Wu |
| author_facet | Lei Yang Guowu Yuan Hao Zhou Hongyu Liu Jian Chen Hao Wu |
| author_sort | Lei Yang |
| collection | DOAJ |
| description | Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS-YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high-performance remote sensing object detector, we combined the trained model with an open-source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA-v1.5, TGRS-HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets. |
| first_indexed | 2024-03-10T03:01:38Z |
| format | Article |
| id | doaj.art-46672e68595f44649aba658250b50516 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:01:38Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-46672e68595f44649aba658250b505162023-11-23T12:45:35ZengMDPI AGApplied Sciences2076-34172022-08-011217870710.3390/app12178707RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing ImagesLei Yang0Guowu Yuan1Hao Zhou2Hongyu Liu3Jian Chen4Hao Wu5School of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650504, ChinaAutomatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS-YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high-performance remote sensing object detector, we combined the trained model with an open-source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA-v1.5, TGRS-HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets.https://www.mdpi.com/2076-3417/12/17/8707object detectionremote sensing imageattention mechanismsfeature fusionvarifocal lossSlicing Aided Hyper Inference (SAHI) |
| spellingShingle | Lei Yang Guowu Yuan Hao Zhou Hongyu Liu Jian Chen Hao Wu RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images Applied Sciences object detection remote sensing image attention mechanisms feature fusion varifocal loss Slicing Aided Hyper Inference (SAHI) |
| title | RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images |
| title_full | RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images |
| title_fullStr | RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images |
| title_full_unstemmed | RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images |
| title_short | RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images |
| title_sort | rs yolox a high precision detector for object detection in satellite remote sensing images |
| topic | object detection remote sensing image attention mechanisms feature fusion varifocal loss Slicing Aided Hyper Inference (SAHI) |
| url | https://www.mdpi.com/2076-3417/12/17/8707 |
| work_keys_str_mv | AT leiyang rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages AT guowuyuan rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages AT haozhou rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages AT hongyuliu rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages AT jianchen rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages AT haowu rsyoloxahighprecisiondetectorforobjectdetectioninsatelliteremotesensingimages |