Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images
Object detection in remote sensing images faces the challenges of a complex background, large object size variations, and high inter-class similarity. To address these problems, we propose an adaptive adjacent layer feature fusion (AALFF) method, which is developed on the basis of RTMDet. Specifical...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4224 |
| _version_ | 1827727930593116160 |
|---|---|
| author | Xuesong Zhang Zhihui Gong Haitao Guo Xiangyun Liu Lei Ding Kun Zhu Jiaqi Wang |
| author_facet | Xuesong Zhang Zhihui Gong Haitao Guo Xiangyun Liu Lei Ding Kun Zhu Jiaqi Wang |
| author_sort | Xuesong Zhang |
| collection | DOAJ |
| description | Object detection in remote sensing images faces the challenges of a complex background, large object size variations, and high inter-class similarity. To address these problems, we propose an adaptive adjacent layer feature fusion (AALFF) method, which is developed on the basis of RTMDet. Specifically, the AALFF method incorporates an adjacent layer feature fusion enhancement (ALFFE) module, designed to capture high-level semantic information and accurately locate object spatial positions. ALFFE also effectively preserves small objects by fusing adjacent layer features and employs involution to aggregate contextual information in a wide spatial range for object essential features extraction in complex backgrounds. Additionally, the adaptive spatial feature fusion (ASFF) module is introduced to guide the network to select and fuse the crucial features to improve the adaptability to objects with different sizes. The proposed method achieves mean average precision (mAP) values of 77.1%, 88.9%, and 95.7% on the DIOR, HRRSD, and NWPU VHR-10 datasets, respectively. Notably, our approach achieves mAP<sub>75</sub> values of 60.8% and 79.0% on the DIOR and HRRSD datasets, respectively, surpassing the state-of-the-art performance on the DIOR dataset. |
| first_indexed | 2024-03-10T23:14:55Z |
| format | Article |
| id | doaj.art-f8290afc89f447fbb4b9c41d115be445 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:14:55Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f8290afc89f447fbb4b9c41d115be4452023-11-19T08:46:13ZengMDPI AGRemote Sensing2072-42922023-08-011517422410.3390/rs15174224Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing ImagesXuesong Zhang0Zhihui Gong1Haitao Guo2Xiangyun Liu3Lei Ding4Kun Zhu5Jiaqi Wang6Institute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaObject detection in remote sensing images faces the challenges of a complex background, large object size variations, and high inter-class similarity. To address these problems, we propose an adaptive adjacent layer feature fusion (AALFF) method, which is developed on the basis of RTMDet. Specifically, the AALFF method incorporates an adjacent layer feature fusion enhancement (ALFFE) module, designed to capture high-level semantic information and accurately locate object spatial positions. ALFFE also effectively preserves small objects by fusing adjacent layer features and employs involution to aggregate contextual information in a wide spatial range for object essential features extraction in complex backgrounds. Additionally, the adaptive spatial feature fusion (ASFF) module is introduced to guide the network to select and fuse the crucial features to improve the adaptability to objects with different sizes. The proposed method achieves mean average precision (mAP) values of 77.1%, 88.9%, and 95.7% on the DIOR, HRRSD, and NWPU VHR-10 datasets, respectively. Notably, our approach achieves mAP<sub>75</sub> values of 60.8% and 79.0% on the DIOR and HRRSD datasets, respectively, surpassing the state-of-the-art performance on the DIOR dataset.https://www.mdpi.com/2072-4292/15/17/4224adjacent layer featureobject detectionremote sensing image |
| spellingShingle | Xuesong Zhang Zhihui Gong Haitao Guo Xiangyun Liu Lei Ding Kun Zhu Jiaqi Wang Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images Remote Sensing adjacent layer feature object detection remote sensing image |
| title | Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images |
| title_full | Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images |
| title_fullStr | Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images |
| title_full_unstemmed | Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images |
| title_short | Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images |
| title_sort | adaptive adjacent layer feature fusion for object detection in remote sensing images |
| topic | adjacent layer feature object detection remote sensing image |
| url | https://www.mdpi.com/2072-4292/15/17/4224 |
| work_keys_str_mv | AT xuesongzhang adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT zhihuigong adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT haitaoguo adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT xiangyunliu adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT leiding adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT kunzhu adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages AT jiaqiwang adaptiveadjacentlayerfeaturefusionforobjectdetectioninremotesensingimages |