Cross-modality Features Fusion for Synthetic Aperture Radar Image Segmentation

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; p. 1
• Main Authors: Gao, Fei, Huang, Heqing, Yue, Zhenyu, Li, Dongyu, Ge, Shuzhi Sam, Lee, Tong Heng, Zhou, Huiyu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Coders; conditional random field; Conditional random fields; Context modeling; Convolutional neural networks; cross-modality features; Data mining; Feature extraction; fully convolutional network; Image enhancement; Image processing; Image segmentation; Pixels; Radar; Radar imaging; Radar polarimetry; SAR (radar); Synthetic aperture radar; Transformers

Synthetic Aperture Radar (SAR) image segmentation stands as a formidable research frontier within the domain of SAR image interpretation. The fully convolutional network (FCN) methods have recently brought remarkable improvements in SAR image segmentation. Nevertheless, these methods do not utilize...