Statistics Learning Network Based on the Quadratic Form for SAR Image Classification

Autor: Xinlong Liu, Bokun He, Chu He, Mingsheng Liao, Chenyao Kang
Rok vydání: 2019
Předmět:
Synthetic aperture radar
Computer science
Science
Computer Science::Neural and Evolutionary Computation
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
0211 other engineering and technologies
02 engineering and technology
Convolutional neural network
Quadratic equation
Statistics
0202 electrical engineering
electronic engineering
information engineering
Mathematics::Metric Geometry
021101 geological & geomatics engineering
Synthetic Aperture Radar (SAR)
Quantitative Biology::Neurons and Cognition
quadratic primitive
Contextual image classification
statistical model
image interpretation
Statistical model
Quadratic form
Computer Science::Computer Vision and Pattern Recognition
statistics learning
Linear algebra
General Earth and Planetary Sciences
020201 artificial intelligence & image processing
Zdroj: Remote Sensing
Volume 11
Issue 3
Remote Sensing, Vol 11, Iss 3, p 282 (2019)
ISSN: 2072-4292
DOI: 10.3390/rs11030282
Popis: The convolutional neural network (CNN) has shown great potential in many fields
however, transferring this potential to synthetic aperture radar (SAR) image interpretation is still a challenging task. The coherent imaging mechanism causes the SAR signal to present strong fluctuations, and this randomness property calls for many degrees of freedom (DoFs) for the SAR image description. In this paper, a statistics learning network (SLN) based on the quadratic form is presented. The statistical features are expected to be fitted in the SLN for SAR image representation. (i) Relying on the quadratic form in linear algebra theory, a quadratic primitive is developed to comprehensively learn the elementary statistical features. This primitive is an extension to the convolutional primitive that involves both nonlinear and linear transformations and provides more flexibility in feature extraction. (ii) With the aid of this quadratic primitive, the SLN is proposed for the classification task. In the SLN, different types of statistics of SAR images are automatically extracted for representation. Experimental results on three datasets show that the SLN outperforms a standard CNN and traditional texture-based methods and has potential for SAR image classification.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje