PolSAR Image Building Extraction with G0 Statistical Texture Using Convolutional Neural Network and Superpixel

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2023-03, Vol.15 (5), p.1451
• Main Authors: Li, Mei, Shen, Qikai, Xiao, Yun, Liu, Xiuguo, Chen, Qihao
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial neural networks; building extraction; Buildings; Classification; CNN; Decomposition; Deep learning; False alarms; Feature extraction; G0 statistical texture; Machine learning; Neural networks; Parameters; Polarimetry; PolSAR; Probability distribution; Radar imaging; Radarsat; Remote sensing; Statistics; superpixel; Synthetic aperture radar; Texture; Urban areas; Variables
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15051451

Polarimetric synthetic aperture radar (PolSAR) has unique advantages in building extraction due to its sensitivity to building structures and all-time/all-weather imaging capabilities. However, the structure of buildings is complex, and buildings are easily confused with other objects in polarimetric SAR images. The speckle noise of SAR images will affect the accuracy of building extraction. This paper proposes a novel building extraction approach from PolSAR images with statistical texture and polarization features by using a convolutional neural network and superpixel. A feature space that is sensitive to building, including G0 statistical texture and PualiRGB features, is constructed and used as CNN input. Considering that the building boundary of the CNN classification result is inaccurate due to speckle noise, the simple linear iterative cluster (SLIC) superpixel is utilized to constrain the building extraction result. Finally, the effectiveness of the proposed method has been verified by experimenting with PolSAR images from three different sensors, including ESAR, GF-3, and RADARSAT-2. Experiment results show that compared with the other five PolSAR building extraction methods including threshold, SVM, RVCNN, and PFDCNN, our method without superpixel constraint, the F1-score of this method is the highest, reaching 84.22%, 91.24%, and 87.49%, respectively. The false alarm rate of this method is at least 10% lower and the F1 index is at least 6% higher when the building extraction accuracy is comparable. Further, the discussion and method parameter analysis results show that increasing the use of G0 statistical texture parameters can improve building extraction accuracy and reduce false alarms, and the introduction of superpixel constraints can further reduce false alarms.