RSTNet提升嘈杂SAR图像中微小目标的识别准确率
RSTNet: Enhancing Small-Target Recognition in Noisy SAR Imagery via Robust Feature Learning and Distribution-Aware Regression
- 采用大核通道分离去噪与多尺度注意力，保留微小船体特征
- 在SSDD数据集上达到98.9% [email protected]，召回率达95.1%
- 适合海上监测、舰船识别等低信噪比场景应用
SAR支持全天候海洋观测，但船舶识别受斑点噪声、复杂海陆背景和微小船只影响，导致大量误检与漏检。我们基于YOLOv8构建自适应的SAR稳定检测模型RSTNet：采用大核通道分离去噪单元消除噪声并保留精细船体特征；通过并行块感知注意力增强微小目标的多尺度特征提取；用NWD损失替代传统IoU损失实现精准边界框回归。该模型在SSDD数据集上表现优于原始YOLOv8，达97.0%精确率、95.1%召回率和98.9% [email protected]。在HRSID数据集上的验证表明其对沿海微小船只具有良好的泛化能力。本工作为含噪声微小目标的海洋观测成像提供了有效技术方案。源代码已开源：https://github.com/renhcmhx/SAR.git。
原文摘要 · Abstract (English)
SAR supports all-day-and-night oceanic observation, yet vessel identification from SAR images is hampered by speckle noise, intricate land-sea backgrounds and dim miniature vessels, yielding numerous false identifications and missed targets. We develop an SAR-adaptive stable detection model RSTNet based on YOLOv8. A large-kernel channel-separated denoising unit eliminates noise and reserves delicate vessel features; parallel patch-aware attention enhances multi-scale feature extraction for miniature objects; NWD loss substitutes conventional IoU loss to achieve accurate bounding box regression. The proposed model outperforms the original YOLOv8 on the SSDD dataset with 97.0% precision, 95.1% recall and 98.9% [email protected]. Validations on the HRSID dataset verify its favorable generalization capacity for coastal miniature vessels. Therefore, our work delivers an effective technical scheme for ocean observation imaging with noisy miniature targets. The source code is available at https://github.com/renhcmhx/SAR.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。