A Scale-Aware Pyramid Network for Multi-Scale Object Detection in SAR Images

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...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2022-02, Vol.14 (4), p.973
Main Authors: Tang, Linbo, Tang, Wei, Qu, Xin, Han, Yuqi, Wang, Wenzheng, Zhao, Baojun
Format: Article
Language:English
Subjects:
Algorithms
Aspect ratio
Convolution
convolutional neural network
Detectors
Feature extraction
feature pyramid network
Feature selection
Localization
Misalignment
Modules
multi-scale object detection
Object recognition
Radar detection
Radar imaging
Remote sensing
Remote sensing systems
Semantics
Synthetic aperture radar
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14040973