Kang Sun

Dr. Kang Sun


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
13 February 2015 in Water
Verified
Journal Article
Open access
PDF file
LJLuyan Ji
Luyan Ji
XGXiurui Geng
Xiurui Geng
KSKang Sun
Kang Sun
YZYongchao Zhao
Yongchao Zhao
PGPeng Gong
Peng Gong
Extracting surface water distribution with satellite imagery has been an important subject in remote sensing. Spectral indices of water only use information from a limited number of bands, thus they may have poor performance from pixels contaminated by ice/snow, clouds, etc. The detection algorithms using information from all spectral bands, such as constrained energy minimization (CEM), could avoid this problem to some extent. However, these are mostly designed for hyperspectral imagery, and may fail when applied to multispectral data. It has been proved that adding linearly irrelevant data to original data could improve the performance of CEM. In this study, two kinds of linearly irrelevant data are added for water extraction: the spectral indices and the spectral similarity metric data. CEM is designed for targets with low-probability distribution in an image, but water bodies do not always satisfy this condition. We thereby impose a sensible coefficient for each pixel to form the weighted autocorrelation matrix. In this study, the weight is based on the orthogonal subspace projection, so this new method is named Orthogonal subspace projection Weighted CEM (OWCEM). The newly launched Landsat 8 images over two lakes, the Hala Lake in China with ice/snow distributed in the north, and the Huron Lake in North America, a lake with a very large surface area, are selected to test the accuracy and robustness of our algorithm. The Kappa coefficient and the receiver operating characteristic (ROC) curve are calculated as an accuracy evaluation standard. For both lakes, our method can greatly suppress the background (including ice/snow and clouds) and extract the complete water surface with a high accuracy (Kappa coefficient > 0.96).

2 December 2014 in Remote Sensing Letters
Verified
Journal Article
Closed access
XGXiurui Geng
Xiurui Geng
KSKang Sun
Kang Sun
LJLuyan Ji
Luyan Ji
Band selection (BS) has been one of the hottest issues in the field of hyperspectral data analysis. Among the existing BS techniques, most of them are designed for classification and few of them are for target detection. In this article, we present a BS method designed specifically for target detection using sparse constrained energy minimization (CEM), named sparse constrained band selection (SCBS). SCBS is a supervised BS method embedded in CEM, which regularizes the CEM operator with a sparse constraint. Then, the sparse model is converted into a standard convex quadratic programming model where the global optimal solution can be obtained conveniently. The validation experiments show that SCBS is superior to the other compared BS methods in terms of target detection.

15 April 2015 in Scientific Reports
Verified
Journal Article
Open access
PDF file
XGXiurui Geng
Xiurui Geng
KSKang Sun
Kang Sun
LJLuyan Ji
Luyan Ji
HTHairong Tang
Hairong Tang
YZYongchao Zhao
Yongchao Zhao
Few band selection methods are specially designed for small target detection. It is well known that the information of small targets is most likely contained in non-Gaussian bands, where small targets are more easily separated from the background. On the other hand, correlation of band set also plays an important role in the small target detection. When the selected bands are highly correlated, it will be unbeneficial for the subsequent detection. However, the existing non-Gaussianity-based band selection methods have not taken the correlation of bands into account, which generally result in high correlation of obtained bands. In this paper, combining the third-order (third-order tensor) and second-order (correlation) statistics of bands, we define a new concept, named joint skewness, for multivariate data. Moreover, we also propose an easy-to-implement approach to estimate this index based on high-order singular value decomposition (HOSVD). Based on the definition of joint skewness, we present an unsupervised band selection for small target detection for hyperspectral data, named joint skewness band selection (JSBS). The evaluation results demonstrate that the bands selected by JSBS are very effective in terms of small target detection.

19 September 2016 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
KSKang Sun
Kang Sun
XGXiurui Geng
Xiurui Geng
JCJinyong Chen
Jinyong Chen
LJLuyan Ji
Luyan Ji
HTHairong Tang
Hairong Tang
MXMiaozhong Xu
Miaozhong Xu
In the field of unsupervised band selection, both robustness and efficiency are of great importance. In this article, we propose a new unsupervised band selection method termed graph representation based band selection (GRBS), which is expected to be insensitive to noisy bands and computationally inexpensive. In GRBS, bands are treated as the nodes of graph in high-dimensional space and centres of the band clusters are considered as the ideal choice. Interestingly, different from other clustering-based band selection methods, GRBS does not involve band clustering. Instead, it employs an easily computed criterion function to select the desired bands, which greatly improves the efficiency. The experiments demonstrate that GRBS has a promising performance and outperforms the compared methods in terms of both accuracy and efficiency.

12 April 2018 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
LMLingbo Meng
Lingbo Meng
XGXiurui Geng
Xiurui Geng
LLLin Li
Lin Li
LJLuyan Ji
Luyan Ji
KSKang Sun
Kang Sun
In [1] , the affiliation for the authors was incorrect in the first footnote. It should be as follows.