HRSF-Net: A High-Resolution Strong Fusion Network for Pixel-Level Classification of the Thin-Stripped Target for Remote Sensing System

• Published in: IEEE journal on miniaturization for air and space systems 2023-12, Vol.4 (4), p.1-1
• Main Authors: Zhou, Lifan, Xing, Wenjie, Zhu, Jie, Xia, Yu, Zhong, Shan, Gong, Shengrong
• Format: Article
• Language: English
• Subjects: Ablation; Artificial neural networks; Classification; Data mining; Datasets; Deep convolutional neural networks; Dual-channel attention; Extreme values; Feature extraction; Feature maps; Hetero-resolution fusion; High resolution; Image resolution; Kernel; Modules; Pixel relationship enhancement; Pixel-level classification; Pixels; Remote sensing; Remote sensing image; Remote sensing systems; Rivers; Roads; Thin-stripped target
• ISSN: 2576-3164; 2576-3164
• DOI: 10.1109/JMASS.2023.3299330

High-resolution pixel-level classification of the roads and rivers in the remote sensing system has extremely important application value and has been a research focus which is received extensive attention from the remote sensing society. In recent years, deep convolutional neural networks (DCNNs) are used in the pixel-level classification of remote sensing image, which has shown extraordinary performance. However, the traditional DCNNs mostly produce discontinuous and incomplete pixel-level classification results when dealing with thin-stripped roads and rivers. To solve the above problem, we put forward a high-resolution strong fusion network (abbreviated as HRSF-Net) which can keep the feature map at high resolution and minimize the texture information loss of the thin-stripped target caused by multiple downsampling operations. In addition, a pixel relationship enhancement and dual-channel attention (PRE-DC) module are proposed to fully explore the strong correlation between the thin-stripped target pixels, and a hetero-resolution fusion (HRF) module is also proposed to better fuse the feature maps with different resolutions. The proposed HRSF-Net is examined on the two public remote sensing datasets. The ablation experimental result verifies the effectiveness of each module of the HRSF-Net. The comparative experimental result shows that the HRSF-Net has achieved mIoU of 79.05% and 64.46% on the two datasets respectively, which both outperform some advanced pixel-level classification methods.