Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method
Multi-scale object detection is critical for analyzing remote sensing images. Traditional feature pyramid networks, which are aimed at accommodating objects of varying sizes through multi-level feature extraction, face significant challenges due to the diverse scale variations present in remote sens...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/5/907 |
| _version_ | 1827319403208769536 |
|---|---|
| author | Chun Liu Sixuan Zhang Mengjie Hu Qing Song |
| author_facet | Chun Liu Sixuan Zhang Mengjie Hu Qing Song |
| author_sort | Chun Liu |
| collection | DOAJ |
| description | Multi-scale object detection is critical for analyzing remote sensing images. Traditional feature pyramid networks, which are aimed at accommodating objects of varying sizes through multi-level feature extraction, face significant challenges due to the diverse scale variations present in remote sensing images. This situation often forces single-level features to span a broad spectrum of object sizes, complicating accurate localization and classification. To tackle these challenges, this paper proposes an innovative algorithm that incorporates an adaptive multi-scale feature enhancement and fusion module (ASEM), which enhances remote sensing image object detection through sophisticated multi-scale feature fusion. Our method begins by employing a feature pyramid to gather coarse multi-scale features. Subsequently, it integrates a fine-grained feature extraction module at each level, utilizing atrous convolutions with varied dilation rates to refine multi-scale features, which markedly improves the information capture from widely varied object scales. Furthermore, an adaptive enhancement module is applied to the features of each level by employing an attention mechanism for feature fusion. This strategy concentrates on the features of critical scale, which significantly enhance the effectiveness of capturing essential feature information. Compared with the baseline method, namely, Rotated FasterRCNN, our method achieved an mAP of 74.21% ( 0.81%) on the DOTA-v1.0 dataset and an mAP of 84.90% (+9.2%) on the HRSC2016 dataset. These results validated the effectiveness and practicality of our method and demonstrated its significant application value in multi-scale remote sensing object detection tasks. |
| first_indexed | 2024-04-25T00:20:14Z |
| format | Article |
| id | doaj.art-8cfba671a0a2479e85890adccf2f281d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-25T00:20:14Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8cfba671a0a2479e85890adccf2f281d2024-03-12T16:54:23ZengMDPI AGRemote Sensing2072-42922024-03-0116590710.3390/rs16050907Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion MethodChun Liu0Sixuan Zhang1Mengjie Hu2Qing Song3Pattern Recognition and Intelligent Vision (PRIV), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaPattern Recognition and Intelligent Vision (PRIV), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaPattern Recognition and Intelligent Vision (PRIV), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaPattern Recognition and Intelligent Vision (PRIV), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaMulti-scale object detection is critical for analyzing remote sensing images. Traditional feature pyramid networks, which are aimed at accommodating objects of varying sizes through multi-level feature extraction, face significant challenges due to the diverse scale variations present in remote sensing images. This situation often forces single-level features to span a broad spectrum of object sizes, complicating accurate localization and classification. To tackle these challenges, this paper proposes an innovative algorithm that incorporates an adaptive multi-scale feature enhancement and fusion module (ASEM), which enhances remote sensing image object detection through sophisticated multi-scale feature fusion. Our method begins by employing a feature pyramid to gather coarse multi-scale features. Subsequently, it integrates a fine-grained feature extraction module at each level, utilizing atrous convolutions with varied dilation rates to refine multi-scale features, which markedly improves the information capture from widely varied object scales. Furthermore, an adaptive enhancement module is applied to the features of each level by employing an attention mechanism for feature fusion. This strategy concentrates on the features of critical scale, which significantly enhance the effectiveness of capturing essential feature information. Compared with the baseline method, namely, Rotated FasterRCNN, our method achieved an mAP of 74.21% ( 0.81%) on the DOTA-v1.0 dataset and an mAP of 84.90% (+9.2%) on the HRSC2016 dataset. These results validated the effectiveness and practicality of our method and demonstrated its significant application value in multi-scale remote sensing object detection tasks.https://www.mdpi.com/2072-4292/16/5/907feature fusionremote sensingobject detectionattention mechanism |
| spellingShingle | Chun Liu Sixuan Zhang Mengjie Hu Qing Song Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method Remote Sensing feature fusion remote sensing object detection attention mechanism |
| title | Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method |
| title_full | Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method |
| title_fullStr | Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method |
| title_full_unstemmed | Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method |
| title_short | Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method |
| title_sort | object detection in remote sensing images based on adaptive multi scale feature fusion method |
| topic | feature fusion remote sensing object detection attention mechanism |
| url | https://www.mdpi.com/2072-4292/16/5/907 |
| work_keys_str_mv | AT chunliu objectdetectioninremotesensingimagesbasedonadaptivemultiscalefeaturefusionmethod AT sixuanzhang objectdetectioninremotesensingimagesbasedonadaptivemultiscalefeaturefusionmethod AT mengjiehu objectdetectioninremotesensingimagesbasedonadaptivemultiscalefeaturefusionmethod AT qingsong objectdetectioninremotesensingimagesbasedonadaptivemultiscalefeaturefusionmethod |