Abstract
Remote sensing imagery (RSI) often involves complex backgrounds and multiscale targets, while variations such as rotation and scaling significantly degrade the performance of existing object detection algorithms and hinder effective modeling of spatial relationships between objects. To address these challenges, we propose SFE-CapsNet. First, we fuse scalar features extracted by convolutional neural networks (CNNs) with vector features from capsule networks through structural reorganization to form virtual capsules, approximating the dynamic routing process via a single fully connected layer. This design preserves object pose and texture information while streamlining information flow. Second, we introduce a capsule attention module (CAM) that generates attention masks to dynamically enhance target-relevant features and suppress background noise, strengthening multilevel feature representations. Integrated with a feature pyramid network (FPN) architecture, our approach achieves precise detection of targets at varying scales. Experimental results demonstrate that multilevel feature fusion and the capsule attention mechanism significantly improve detection accuracy and robustness, achieving 77.65% mean average precision (mAP) on the DOTA dataset and 97.63% mAP on HRSC2016, highlighting its effectiveness and efficiency in complex scenes.
| Original language | English |
|---|---|
| Article number | 6000905 |
| Journal | IEEE Geoscience and Remote Sensing Letters |
| Volume | 23 |
| DOIs | |
| State | Published - 2026 |
| Externally published | Yes |
Keywords
- Attention mechanism
- capsule networks
- convolutional neural networks (CNNs)
- object detection
- remote sensing images
Fingerprint
Dive into the research topics of 'SFE-CapsNet: Spatial Feature Enhanced Capsule Networks for Remote Sensing Object Detection'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver