Journal
REMOTE SENSING
Volume 14, Issue 4, Pages -Publisher
MDPI
DOI: 10.3390/rs14040973
Keywords
synthetic aperture radar; multi-scale object detection; feature pyramid network; convolutional neural network
Categories
Funding
- China Postdoctoral Science Foundation [2021TQ0177]
- Shandong Natural Science Foundation [ZR2021MF021]
Ask authors/readers for more resources
A scale-aware feature pyramid network (SARFNet) is proposed for multi-scale object detection within Synthetic Aperture Radar (SAR) images. The network incorporates a feature alignment module, a scale-equalizing pyramid convolution, and a self-learning anchor assignment strategy to flexibly match targets with different appearance changes.
Multi-scale object detection within Synthetic Aperture Radar (SAR) images has become a research hotspot in SAR image interpretation. Over the past few years, CNN-based detectors have advanced sharply in SAR object detection. However, the state-of-the-art detection methods are continuously limited in Feature Pyramid Network (FPN) designing and detection anchor setting aspects due to feature misalignment and targets' appearance variation (i.e., scale change, aspect ratio change). To address the mentioned limitations, a scale-aware feature pyramid network (SARFNet) is proposed in this study, which comprises a scale-adaptive feature extraction module and a learnable anchor assignment strategy. To be specific, an enhanced feature pyramid sub-network is developed by introducing a feature alignment module to estimate the pixel offset and contextually align the high-level features. Moreover, a scale-equalizing pyramid convolution is built through 3-D convolution within the feature pyramid to improve inter-scale correlation at different feature levels. Furthermore, a self-learning anchor assignment is set to update hand-crafted anchor assignments to learnable anchor/feature configuration. By using the dynamic anchors, the detector of this study is capable of flexibly matching the target with different appearance changes. According to extensive experiments on public SAR image data sets (SSDD and HRSID), our algorithm is demonstrated to outperform existing boat detectors.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available