Xianchuan Yu

Prof. Dr. Xianchuan Yu

School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
22 April 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ZZZhengang Zhao
Zhengang Zhao
DHDan Hu
Dan Hu
HWHao Wang
Hao Wang
Xianchuan YuXianchuan Yu
Xianchuan Yu
Convolutional neural networks (CNNs) have attained remarkable performance in hyperspectral image (HSI) classification. However, the existing CNNs are restricted by their limited receptive field in HSI classification. Recently, transformer networks have proved to be promising in many tasks thanks to the global receptive field, but they easily ignore some local information that is important for HSI classification. In this letter, we propose a novel method entitled convolutional transformer network (CTN) for HSI classification. In order to make full use of spectral information and spatial information, the method adopts center position encoding (CPE) to merge spectral features and pixel positions. Furthermore, the proposed method introduces convolutional transformer (CT) blocks. It effectively combines convolution and transformer structures together to capture local–global features of HSI patches, which is contributive for HSI classification. Experimental results on public datasets demonstrate the superiority of our method compared with several state-of-the-art classification methods. The codes of this work will be available at https://github.com/sky8791 to facilitate reproducibility.

27 January 2014 in Science China Earth Sciences
Verified
Journal Article
Closed access
PDF file
Xianchuan YuXianchuan Yu
Xianchuan Yu
HHHui He
Hui He
DHDan Hu
Dan Hu
WZWei Zhou
Wei Zhou

11 September 2018 in Science China Earth Sciences
Verified
Journal Article
Closed access
PDF file
HHHui He
Hui He
HXHaihua Xing
Haihua Xing
DHDan Hu
Dan Hu
Xianchuan YuXianchuan Yu
Xianchuan Yu

1 January 2015 in Journal of Applied Remote Sensing
Verified
Journal Article
Closed access
PDF file
YZYinggang Zhang
Yinggang Zhang
LZLibao Zhang
Libao Zhang
Xianchuan YuXianchuan Yu
Xianchuan Yu
Region of interest (ROI) extraction is an important component of remote sensing image processing. However, traditional ROI extraction methods are usually prior knowledge-based and depend on classification, segmentation, and a global searching solution, which are time-consuming and computationally complex. We propose a more efficient ROI extraction model for remote sensing images based on multiscale visual saliency analysis (MVS), implemented in the CIE L*a*b* color space, which is similar to visual perception of the human eye. We first extract the intensity, orientation, and color feature of the image using different methods: the visual attention mechanism is used to eliminate the intensity feature using a difference of Gaussian template; the integer wavelet transform is used to extract the orientation feature; and color information content analysis is used to obtain the color feature. Then, a new feature-competition method is proposed that addresses the different contributions of each feature map to calculate the weight of each feature image for combining them into the final saliency map. Qualitative and quantitative experimental results of the MVS model as compared with those of other models show that it is more effective and provides more accurate ROI extraction results with fewer holes inside the ROI.

17 May 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
RMRong Ma
Rong Ma
HTHaifeng Tian
Haifeng Tian
Xiaochun ChengXiaochun Cheng
Xiaochun Cheng
YXYi Xiao
Yi Xiao
QXQingxiao Xu
Qingxiao Xu
Xianchuan YuXianchuan Yu
Xianchuan Yu
Working conditions identification of oil well relies on high-cost and slow-speed artificial inspection in past decades. Working conditions diagnosis through dynamometer cards identification based on machine learning has significant economic value and environmental meaning for oil production. In this paper, we collect dynamometer cards from the famous Chinese Shengli Oil Field as research data. We firstly investigate properties of dynamometers under different working conditions and create a dynamometer card dataset. Further we introduce calibration/visualization preprocess methods, and propose the Oil-Net 1D/2D identification models from the time-series and computer vision views respectively. Experiment results indicate that comparing with other machine learning and time series classification methods, Oil-Net 1D/2D improve identification accuracy significantly. This study provides guidance for the design and implementation of learning-based oil well working conditions intelligent diagnosis system.

29 February 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YZYing Zhan
Ying Zhan
DHDan Hu
Dan Hu
Xianchuan YuXianchuan Yu
Xianchuan Yu
YWYufeng Wang
Yufeng Wang
Hyperspectral remote sensing images (HSIs) have both spectral and spatial characteristics. The adept exploitation of these attributes is central to enhancing the classification accuracy of HSIs. In order to effectively utilize spatial and spectral features to classify HSIs, this paper proposes a method for the spatial feature extraction of HSIs based on a mutually guided image filter (muGIF) and combined with the band-distance-grouped principal component. Firstly, aiming at the problem that previously guided image filtering cannot effectively deal with the inconsistent information structure between the guided and target information, a method for extracting spatial features using muGIF is proposed. Then, aiming at the problem of the information loss caused by a single principal component as a guided image in the traditional GIF-based spatial–spectral classification, a spatial feature-extraction framework based on the band-distance-grouped principal component is proposed. The method groups the bands according to the band distance and extracts the principal components of each set of band subsets as the guide map of the current band subset to filter the HSIs. A deep convolutional neural network model and a generative adversarial network model for the filtered HSIs are constructed and then trained using samples for HSIs’ spatial–spectral classification. Experiments show that compared with the traditional methods and several popular spatial–spectral HSI classification methods based on a filter, the proposed methods based on muGIF can effectively extract the spatial–spectral features and improve the classification accuracy of HSIs.