A Lightweight Theory-Driven Network and Its Validation on Public Fully Polarized Ship Detection Dataset
Open Access
- 16 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3755-3767
Abstract
The utilization of polarimetric synthetic aperture radar (PolSAR) enables the preservation of more comprehensive target scattering characteristics compared to conventional SAR. Despite the significant advancements in deep learning (DL) technology for single polarimetric SAR ship detection, there remains a scarcity of DL research specifically focused on PolSAR ship detection. This article proposed a lightweight theory-driven network (LT-Net) for combining domain knowledge and DL techniques, which is suitable to detect small targets and reduce the computational complexity. The LT-Net incorporates convolutional block attention module, and employs differential downsampling during the process of high-dimensional feature extraction. The integration of domain knowledge lends each convolution step a distinct physical significance. Due to the limited availability of public datasets, this article presents a public fully polarized ship detection (FPSD) dataset for the first time, which contains 853 Pauli pseudocolor maps (in JPG format) and multilook complex data (in TIF format), with a total of 1714 ship targets from AIRSAR, UAVSAR, and RadarSAT-2. The FPSD encompasses a range of scenarios, with the majority of ship targets being small targets. Validation on FPSD shows that LT-Net exhibits significantly lower time complexity and space complexity compared to four popular target detection networks, Meanwhile, LT-Net achieves the best detection performance in the Pauli pseudocolor maps.Keywords
Funding Information
- National Natural Science Foundation of China (62171452, 61771483)
This publication has 40 references indexed in Scilit:
- Synthetic Aperture Radar (SAR) for Ocean: A ReviewIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
- An improved fire detection approach based on YOLO-v8 for smart citiesNeural Computing and Applications, 2023
- Dualistic cascade convolutional neural network dedicated to fully PolSAR image ship detectionISPRS Journal of Photogrammetry and Remote Sensing, 2023
- PolSAR Ship Detection Based on Azimuth Sublook Polarimetric Covariance MatrixIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
- Searching Central Difference Convolutional Networks for Face Anti-Spoofing2020
- CBAM: Convolutional Block Attention Module2018
- Deep learningNature, 2015
- A Notch Filter for Ship Detection With Polarimetric SAR DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013
- Reflection Symmetry for Polarimetric Observation of Man-Made Metallic Targets at SeaIEEE Journal of Oceanic Engineering, 2012
- Generalized Optimization of Polarimetric Contrast EnhancementIEEE Geoscience and Remote Sensing Letters, 2004