A Lightweight Complex-Valued DeepLabv3+ for Semantic Segmentation of PolSAR Image

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 15; pp. 930 - 943
• Main Authors: Yu, Lingjuan, Zeng, Zhaoxin, Liu, Ao, Xie, Xiaochun, Wang, Haipeng, Xu, Feng, Hong, Wen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Convolution; Datasets; Decoding; Feature extraction; Image classification; Image processing; Image segmentation; Kernel; Lightweight; Lightweight complex-valued DeepLabv3+ (L-CV-DeepLabv3+); Pixels; polarimteric synthetic aperture radar (SAR); Radar imaging; SAR (radar); Scattering; segmentation performance; semantic image segmentation; Semantic segmentation; Semantics; Synthetic aperture radar
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2021.3140101

Semantic image segmentation is one kindof end-to-end segmentation method which can classify the target region pixel by pixel. As a classic semantic segmentation network in optical images, DeepLabv3+ can achieve a good segmentation performance. However, when this network is directly used in the semantic segmentation of polarimetric synthetic aperture radar (PolSAR) image, it is hard to obtain the ideal segmentation results. The reason is that it is easy to yield overfitting due to the small PolSAR dataset. In this article, a lightweight complex-valued DeepLabv3+ (L-CV-DeepLabv3+) is proposed for semantic segmentation of PolSAR data. It has two significant advantages when compared with the original DeepLabv3+. First, the proposed network with the simplified structure and parameters can be suitable for the small PolSAR data, and thus, it can effectively avoid the overfitting. Second, the proposed complex-valued (CV) network can make full use of both amplitude and phase information of PolSAR data, which brings better segmentation performance than the real-valued (RV) network, and the related CV operations are strictly true in the mathematical sense. Experimental results about two Flevoland datasets and one San Francisco dataset show that the proposed network can obtain better overall average, mean intersection over union, and mean pixel accuracy than the original DeepLabv3+ and some other RV semantic segmentation networks.