Back to Search
Start Over
SEL-Net: A Self-Supervised Learning-Based Network for PolSAR Image Runway Region Detection
- Source :
- Remote Sensing, Vol 15, Iss 19, p 4708 (2023)
- Publication Year :
- 2023
- Publisher :
- MDPI AG, 2023.
-
Abstract
- This paper proposes an information enhancement network based on self-supervised learning (SEL-Net) for runway area detection. During the self-supervised learning phase, the distinctive attributes of PolSAR multi-channel data are fully harnessed to enhance the generated pretrained model’s focus on airport runway areas. During the detection phase, this paper presents an improved U-Net detection network. Edge Feature Extraction Modules (EEM) are integrated into the encoder and skip connection sections, while Semantic Information Transmission Modules (STM) are embedded into the decoder section. Furthermore, improvements have been applied to the network’s upsampling and downsampling architectures. Experimental results demonstrate that the proposed SEL-Net effectively addresses the issues of high false alarms and runway integrity, achieving a superior detection performance.
Details
- Language :
- English
- ISSN :
- 20724292
- Volume :
- 15
- Issue :
- 19
- Database :
- Directory of Open Access Journals
- Journal :
- Remote Sensing
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.3cb1529f9d48898a35c97ef5938837
- Document Type :
- article
- Full Text :
- https://doi.org/10.3390/rs15194708