Yang Du

Dr. Yang Du

School of Information and Electronic Engineering, Zhejiang University, Hangzhou 310058, Zhejiang, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 September 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ZZZheng Zhang
Zheng Zhang
JYJingsong Yang
Jingsong Yang
YDYang Du
Yang Du
Effective and efficient classification of synthetic aperture radar (SAR) images represents an important step toward image interpretation and knowledge discovery. Keys to classification performance include feature extraction and availability of class labels for training. Generative adversarial networks (GANs) are a recently advanced powerful framework to offer both automatic feature extraction and semisupervised and unsupervised learning. For its known drawbacks such as mode collapse and training instability, noteworthy improvements include the deep convolutional GANs (DCGANs). In the letter, we proposed a new approach, which further advances DCGANs with autoencoder (AE) for intermediate feature extraction and reconstruction, in combination with multiclassifier (MC) for better context treatment. The resulting improvement on training stability and mode preservation over DCGAN is clearly demonstrated by the classification results across multifrequency bands (L-, C-, and X-bands).

21 February 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JYJingsong Yang
Jingsong Yang
YLYongxing Li
Yongxing Li
JSJ. C. Shi
J. C. Shi
YDYang Du
Yang Du
In this letter, we modify the extended advanced integral equation model (EAIEM) for electromagnetic backscattering and bistatic scattering from rough surfaces with small to moderate heights. We extend the first-order approximation of the error function as introduced in the EAIEM model to the second order, in a hope to be more suitable for large roughness and high frequency. In addition, a new transition model for the reflection coefficient is proposed to make the dependences explicit on the mean surface curvature, frequency, and dielectric constant, whereas making no use of the complementary term, the effect of inadequate evaluation of this term is mitigated. Comparison with POLARSCAT data for backscattering and with European Microwave Signature Laboratory (EMSL) measurements for bistatic scattering demonstrates the validity of the updated model.

9 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
ZZZheng Zhang
Zheng Zhang
HGHui Guo
Hui Guo
JYJingsong Yang
Jingsong Yang
XWXianggang Wang
Xianggang Wang
YDYang Du
Yang Du
Effective and efficient pixel-level classification of polarimetric synthetic aperture radar (PolSAR) images represents an important step toward their interpretation and knowledge discovery. After the extraction and representation of discriminative features, the related important issues are how to enforce consistency and coherency of labeling using contextual information, and how to make the process computationally efficient. In this article, we propose a method to approach these two issues. The first issue is dealt with from three different levels, namely, first, to combine features at coarse resolution with pixel-wise information for pixel-level classification, we adopt the idea of Unet; second, to reduce labeling inhomogeneity among similar pixels, we relate the PolSAR image with graph theory through the conditional random field (CRF), and develop third-order potentials for a fully connected CRF to account for both higher order effects and long-range interactions; and, third, to utilize adversarial network to improve learning of the label distribution. The efficiency issue is handled by, first, adopting fully convolutional network for the contracting arm of the Unet to speed up hierarchical feature extraction; and, second, for the fully connected third-order potential, by making connection with the pairwise potential, to reduce the computational complexity of the most expensive message passing procedure from quadratic to linear in the number of variables. The effectiveness of the proposed method has been demonstrated by its application to the pixel-level classification of ALOS-2, RADARSAT-2, and ESAR PolSAR images, where its performance has qualitatively and quantitatively shown superiority over several other state-of-the-art models.

1 January 2014
Verified
Book Chapter
Closed access
PDF file
YDYang Du
Yang Du

13 January 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CYChao Yang
Chao Yang
YDYang Du
Yang Du
Electromagnetic scattering from multiple cylinders has been an active research topic in many research fields, and the special case of parallel cylinders has seen important applications ranging from remote sensing to biology. Yet, the rigorous treatments have been mostly focusing on the 2-D cases, whereas for the more realistic 3-D cases, approximated approaches are often adopted. This article proposes a more rigorous treatment of 3-D polarimetric multiple scattering from parallel cylinders by extending our previously proposed virtual partition method (VPM) for single-cylinder case to multiple-cylinder case. The appeal of the method includes the appreciably reduced longitudinal dimension for subcylinders and its corresponding encircling sphere so as to effectively address the otherwise thorny issue of violation of the required mutual exclusion of encircling spheres of large aspect ratio cylinders by the conventional multiple scatterers' equation. The proposed VPM demonstrates the capability of capturing very well the polarimetric bistatic scattering amplitudes and phases, and of meeting physical requirements of energy conservation and reciprocity theorem. A systematic examination of the coupling effect is carried out against a number of factors, including average interneighbor-cylinder (intercylinder for short) distance, cylinder size, dielectric constant, and cylinder number, with the numerical results clearly revealing the complicated pattern of coupling effect. The studied cases suggest that the coupling effect may still be felt for a large average intercylinder distance. For electromagnetic wave propagation in the parallel cylinders, the coupling effect is visible, yet it tends to be mitigated by the average process.

29 August 2018 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
CYChao Yang
Chao Yang
YDYang Du
Yang Du
The capability of reliably describing the electromagnetic scattering behavior by a dielectric finite cylinder is important in many applications, in particular, for microwave remote sensing of vegetated terrain. Previous lack of accurate analytical or semianalytical cylinder scattering model has led to the popularity of the infinite cylinder approximation (ICA) approach even at present. Yet, the performance of ICA has not been systematically quantitatively characterized in the literature. This letter fills in the gap, and demonstrates that ICA leaves much to be desired in many aspects.