Polarimetric Convolutional Network for PolSAR Image Classification

Liu, Xu; Jiao, Licheng; Tang, Xu; Sun, Quansen; Zhang, Dan

doi:10.1109/tgrs.2018.2879984

Cited by 96 publications

(63 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the differences between PolSAR images and optical images, it is advisable to adjust the network architectures to better utilize the unique information of PolSAR. Hand-craft PolSAR features were extracted as the input of CNNs in some studies (Chen and Tao, 2018;Liu et al, 2019b), which are attempts in the right direction. Real-valued primitives operations in CNNs were replaced by complex-valued ones in Zhang et al (2017) and a three-layers complexvalued CNN was modeled.…”

Section: Cnns For Polsar Classificationmentioning

confidence: 99%

“…To evaluate the performance of the involved algorithms, average accuracy (AA), overall accuracy (OA), kappa coefficient (Kappa) and F 1 -score are chosen as criteria, which can be defined as follows (Liu et al, 2019b)…”

Section: Datasets Descriptionmentioning

confidence: 99%

“…Besides, Chen and Tao (2018) used hand-craft PolSAR features as the input of CNNs to improve the performance. A polarimetric scattering coding method was proposed in Liu et al (2019b) to get a new form of input, and a fully convolutional network based classifier was used to obtain better classification results. Inspired by the previous works, a deep learning based PolSAR image classification framework is proposed in this paper based on the proposed input form and multi-task CNN (MCNN).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Zhang

Dong

Zou

2019

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have been widely used to improve the accuracy of polarimetric synthetic aperture radar (PolSAR) image classification. However, in most studies, the difference between PolSAR images and optical images is rarely considered. Most of the existing CNNs are not tailored for the task of PolSAR image classification, in which complex-valued PolSAR data have been simply equated to real-valued data to fit the optical image processing architectures and avoid complex-valued operations. This is one of the reasons CNNs unable to perform their full capabilities in PolSAR classification. To solve the above problem, the objective of this paper is to develop a tailored CNN framework for PolSAR image classification, which can be implemented from two aspects: Seeking a better form of PolSAR data as the input of CNNs and building matched CNN architectures based on the proposed input form. In this paper, considering the properties of complexvalued numbers, amplitude and phase of complex-valued PolSAR data are extracted as the input for the first time to maintain the integrity of original information while avoiding immature complex-valued operations. Then, a multi-task CNN (MCNN) architecture is proposed to match the improved input form and achieve better classification results. Furthermore, depthwise separable convolution is introduced to the proposed architecture in order to better extract information from the phase information. Experiments on three PolSAR benchmark datasets not only prove that using amplitude and phase as the input do contribute to the improvement of PolSAR classifica-

show abstract

Section: Cnns For Polsar Classificationmentioning

confidence: 99%

Section: Datasets Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Zhang

Dong

Zou

2019

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the polarimetric scattering coding (PSC) [9], it assumes that z = (x + yi) is a complex value, x and y are the real and imaginary parts of z respectively. Polarimetric scattering coding ϕ is shown as follows:…”

Section: Polarimetric Scattering Codingmentioning

confidence: 99%

Polsar Image Classification Based on Polarimetric Scattering Coding and Sparse Support Matrix Machine

Liu

Jiao

Zhang

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

Self Cite

View full text Add to dashboard Cite

POLSAR image has an advantage over optical image because it can be acquired independently of cloud cover and solar illumination. PolSAR image classification is a hot and valuable topic for the interpretation of POLSAR image. In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine. First, we transform the original POLSAR data to get a real value matrix by the polarimetric scattering coding, which is called polarimetric scattering matrix and is a sparse matrix. Second, the sparse support matrix machine is used to classify the sparse polarimetric scattering matrix and get the classification map. The combination of these two steps takes full account of the characteristics of POLSAR. The experimental results show that the proposed method can get better results and is an effective classification method.Index Terms-POLSAR image, classification, scattering coding, sparse support matrix machine.

show abstract

“…Deep networks [28] is the third category for SAR image classification, and significant efforts have been made to gradually shift to this paradigm [29][30][31][32][33]. In addition, the convolutional neural network (CNN) [34] can be interpreted as a multilayer mapping function that maps from the input data to the task-related output.…”

Section: Related Workmentioning

confidence: 99%

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

Fan

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Polarimetric Convolutional Network for PolSAR Image Classification

Cited by 96 publications

References 88 publications

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Polsar Image Classification Based on Polarimetric Scattering Coding and Sparse Support Matrix Machine

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

Contact Info

Product

Resources

About