ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images
Remote sensing images play a vital role in domains including environmental monitoring, agriculture, and autonomous driving. However, the detection of targets in remote sensing images remains a challenging task. This study introduces innovative methods to enhance feature extraction, feature fusion, a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/23/7472 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846123849651847168 |
|---|---|
| author | Yijuan Qiu Xiangyue Zheng Xuying Hao Gang Zhang Tao Lei Ping Jiang |
| author_facet | Yijuan Qiu Xiangyue Zheng Xuying Hao Gang Zhang Tao Lei Ping Jiang |
| author_sort | Yijuan Qiu |
| collection | DOAJ |
| description | Remote sensing images play a vital role in domains including environmental monitoring, agriculture, and autonomous driving. However, the detection of targets in remote sensing images remains a challenging task. This study introduces innovative methods to enhance feature extraction, feature fusion, and model optimization. The Adaptive Selective Feature Enhancement Module (AFEM) dynamically adjusts feature weights using GhostModule and sigmoid functions, thereby enhancing the accuracy of small target detection. Moreover, the Adaptive Multi-scale Convolution Kernel Feature Fusion Module (AKSFFM) enhances feature fusion through multi-scale convolution operations and attention weight learning mechanisms. Moreover, our proposed ARSOD-YOLO optimized the network architecture, component modules, and loss functions based on YOLOv8, enhancing outstanding small target detection capabilities while preserving model efficiency. We conducted experiments on the VEDAI and AI-TOD datasets, showcasing the excellent performance of ARSOD-YOLO. Our algorithm achieved an mAP50 of 74.3% on the VEDAI dataset, surpassing the YOLOv8 baseline by 3.1%. Similarly, on the AI-TOD dataset, the mAP50 reached 47.8%, exceeding the baseline network by 6.1%. |
| format | Article |
| id | doaj-art-98ea1d5548794bbbb8873ce67d4554dc |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-98ea1d5548794bbbb8873ce67d4554dc2024-12-13T16:31:38ZengMDPI AGSensors1424-82202024-11-012423747210.3390/s24237472ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing ImagesYijuan Qiu0Xiangyue Zheng1Xuying Hao2Gang Zhang3Tao Lei4Ping Jiang5National Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaNational Laboratory on Adaptive Optics, Chengdu 610209, ChinaRemote sensing images play a vital role in domains including environmental monitoring, agriculture, and autonomous driving. However, the detection of targets in remote sensing images remains a challenging task. This study introduces innovative methods to enhance feature extraction, feature fusion, and model optimization. The Adaptive Selective Feature Enhancement Module (AFEM) dynamically adjusts feature weights using GhostModule and sigmoid functions, thereby enhancing the accuracy of small target detection. Moreover, the Adaptive Multi-scale Convolution Kernel Feature Fusion Module (AKSFFM) enhances feature fusion through multi-scale convolution operations and attention weight learning mechanisms. Moreover, our proposed ARSOD-YOLO optimized the network architecture, component modules, and loss functions based on YOLOv8, enhancing outstanding small target detection capabilities while preserving model efficiency. We conducted experiments on the VEDAI and AI-TOD datasets, showcasing the excellent performance of ARSOD-YOLO. Our algorithm achieved an mAP50 of 74.3% on the VEDAI dataset, surpassing the YOLOv8 baseline by 3.1%. Similarly, on the AI-TOD dataset, the mAP50 reached 47.8%, exceeding the baseline network by 6.1%.https://www.mdpi.com/1424-8220/24/23/7472object detectionremote sensingsmall objectfeature fusion |
| spellingShingle | Yijuan Qiu Xiangyue Zheng Xuying Hao Gang Zhang Tao Lei Ping Jiang ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images Sensors object detection remote sensing small object feature fusion |
| title | ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images |
| title_full | ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images |
| title_fullStr | ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images |
| title_full_unstemmed | ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images |
| title_short | ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images |
| title_sort | arsod yolo enhancing small target detection for remote sensing images |
| topic | object detection remote sensing small object feature fusion |
| url | https://www.mdpi.com/1424-8220/24/23/7472 |
| work_keys_str_mv | AT yijuanqiu arsodyoloenhancingsmalltargetdetectionforremotesensingimages AT xiangyuezheng arsodyoloenhancingsmalltargetdetectionforremotesensingimages AT xuyinghao arsodyoloenhancingsmalltargetdetectionforremotesensingimages AT gangzhang arsodyoloenhancingsmalltargetdetectionforremotesensingimages AT taolei arsodyoloenhancingsmalltargetdetectionforremotesensingimages AT pingjiang arsodyoloenhancingsmalltargetdetectionforremotesensingimages |