Next Article in Journal
Long-Term Dynamics of Sandy Vegetation and Land in North China
Next Article in Special Issue
A Novel Polarization Scattering Decomposition Model and Its Application to Ship Detection
Previous Article in Journal
A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 15
Issue 19
10.3390/rs15194802
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Polarimetric Synthetic Aperture Radar Image Semantic Segmentation Network with Lovász-Softmax Loss Optimization

by
Rui Guo
1,*,
Xiaopeng Zhao
1,
Guanzhong Zuo
1,2,
Ying Wang
1 and
Yi Liang
3
1
School of Automation, Northwestern Polytechnical University, Xi’an 710072, China
2
School of Automation, Beijing Institute of Technology, Beijing 100081, China
3
The National Key Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2023, 15(19), 4802; https://doi.org/10.3390/rs15194802
Submission received: 21 July 2023 / Revised: 20 September 2023 / Accepted: 30 September 2023 / Published: 1 October 2023
(This article belongs to the Special Issue Target Detection with Fully-Polarized Radar)
Browse Figures
Versions Notes

Abstract

The deep learning technique has already been successfully applied in the field of microwave remote sensing. Especially, convolutional neural networks have demonstrated remarkable effectiveness in synthetic aperture radar (SAR) image semantic segmentation. In this paper, a Lovász-softmax loss optimization SAR net (LoSARNet) is proposed which optimizes the semantic segmentation metric intersection over union (IOU) instead of using the traditional cross-entropy loss. Meanwhile, making use of the advantages of the dual-path structure, the network extracts feature through the spatial path (SP) and the context path (CP) to achieve a balance between efficiency and accuracy. Aiming at a polarimetric SAR (PolSAR) image, the proposed network is conducted on the PolSAR datasets for terrain segmentation. Compared to the typical dual-path network, which is the bilateral segmentation network (BiSeNet), the proposed LoSARNet can obtain better mean intersection over union (MIOU). And the proposed network also shows the highest evaluation index and the best performance when compared with several typical networks.
Keywords: polarimetric synthetic aperture radar (SAR); semantic segmentation network; deep learning; loss function; Lovász-softmax loss optimization SAR net (LoSARNet) polarimetric synthetic aperture radar (SAR); semantic segmentation network; deep learning; loss function; Lovász-softmax loss optimization SAR net (LoSARNet)

Share and Cite

MDPI and ACS Style

Guo, R.; Zhao, X.; Zuo, G.; Wang, Y.; Liang, Y. Polarimetric Synthetic Aperture Radar Image Semantic Segmentation Network with Lovász-Softmax Loss Optimization. Remote Sens. 2023, 15, 4802. https://doi.org/10.3390/rs15194802

AMA Style

Guo R, Zhao X, Zuo G, Wang Y, Liang Y. Polarimetric Synthetic Aperture Radar Image Semantic Segmentation Network with Lovász-Softmax Loss Optimization. Remote Sensing. 2023; 15(19):4802. https://doi.org/10.3390/rs15194802

Chicago/Turabian Style

Guo, Rui, Xiaopeng Zhao, Guanzhong Zuo, Ying Wang, and Yi Liang. 2023. "Polarimetric Synthetic Aperture Radar Image Semantic Segmentation Network with Lovász-Softmax Loss Optimization" Remote Sensing 15, no. 19: 4802. https://doi.org/10.3390/rs15194802

APA Style

Guo, R., Zhao, X., Zuo, G., Wang, Y., & Liang, Y. (2023). Polarimetric Synthetic Aperture Radar Image Semantic Segmentation Network with Lovász-Softmax Loss Optimization. Remote Sensing, 15(19), 4802. https://doi.org/10.3390/rs15194802

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop