A Lightweight Deep Learning Framework with Reduced Computational Overhead for Ship Detection in Satellite SAR Imagery
Open Access
- 24 November 2025
- journal article
- research article
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13 (12) , 2234
Abstract
Ship detection plays a pivotal role in safeguarding maritime security, regulating vessel traffic, and bolstering national maritime defense. While contemporary lightweight models predominantly emphasize parameter reduction, efforts to curtail computational demands remain underexplored. In this study, we propose a lightweight multi-feature channel convolution module (MFC-Conv) to create an efficient backbone network. This module adeptly propagates multi-scale feature information, yielding a holistic representation while approximating residual architectures in a computationally frugal manner, thereby promoting seamless gradient flow during optimization. Notably, MFC-Conv can be re-parameterized into a streamlined two-layer convolutional structure devoid of branching or partitioning, streamlining deployment on resource-constrained edge devices. Complementing this, a multi-feature attention module (MFA) is proposed to augment localization and classification efficacy with negligible overhead. Furthermore, leveraging the inherent resolution traits of satellite SAR imagery, the decoder is refined to minimize redundant computations. Empirical evaluations across diverse datasets reveal that our framework outperforms the baseline by slashing parameters by 57.8% and FLOPs by 42.7%. Relative to two leading lightweight state-of-the-art (SOTA) models, it achieves computational reductions of 51.4% and 25.0%, respectively, thereby enabling viable onboard satellite deployment for ship detection.Keywords
Funding Information
- Technology Innovation Center for South China Sea Remote Sensing, Surveying and Mapping Collaborative Application, Ministry of Natural Resources, P.R. China (RSSMCA-2024-B012)
- Science and Technology Development Foundation of South China Sea Bureau, Ministry of Natural Resources (230103)
- National Natural Science Foundation of China (42561060)
This publication has 34 references indexed in Scilit:
- Non-Euclidean Spectral-Spatial feature mining network with Gated GCN-CNN for hyperspectral image classificationExpert Systems with Applications, 2025
- UAV Hyperspectral Remote Sensing Image Classification: A Systematic ReviewIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- A Lightweight SAR Ship Detection Network Based on Deep Multiscale Grouped Convolution, Network Pruning, and Knowledge DistillationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- Strong economic incentives of ship scrubbers promoting pollutionNature Sustainability, 2024
- An Improved Ship Detection Algorithm for an Airborne Passive Interferometric Microwave Sensor (PIMS) Based on Ship WakesIEEE Transactions on Geoscience and Remote Sensing, 2023
- SRCANet: Stacked Residual Coordinate Attention Network for Infrared Ship DetectionIEEE Transactions on Geoscience and Remote Sensing, 2022
- Invisible ship tracks show large cloud sensitivity to aerosolNature, 2022
- Real-time energy consumption and air pollution emission during the transpacific crossing of a container shipScientific Reports, 2022
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018