Search

Your search keyword '"Yu, Xuchu"' showing total 104 results
Start Over Author "Yu, Xuchu"
104 results on '"Yu, Xuchu"'

2. Heterogeneous feature learning network for multimodal remote sensing image collaborative classification.

Author

Yu, Xuchu, Xue, Zhixiang, Yang, Guopeng, Yu, Anzhu, Liu, Bing, and Hu, Qingfeng

Subjects
*IMAGE recognition (Computer vision), *CONVOLUTIONAL neural networks, *REMOTE sensing, *MULTIMODAL user interfaces, *TRANSFORMER models, *FEATURE extraction
Abstract

While multimodal remote sensing data processing has garnered growing interests in the geoscience field, how to effectively extract, represent, and fuse heterogeneous features remains challenging. In this article, a novel heterogeneous feature learning network (HFLN) architecture is investigated for multimodal remote sensing collaborative classification, which takes both advantages of long-range feature modelling capability of transformer as well as local feature extraction of convolutional neural network (CNN). First, the global spectral dependencies are extracted from hyperspectral images using the spectral transformer structure. Then, local spatial invariant characteristics are extracted from multimodal remote sensing images by convolutional operation. Next, heterogeneous spectral and spatial characteristics, having significant structural and semantic differences, are dynamically integrated through the feature coupling module in an interactive manner. Finally, the multi-stage network architecture is utilized for extracting hierarchical characteristics, where the numbers of feature maps in CNN and heads in transformer are gradually increased to represent more complex features. Four benchmark remote sensing datasets (i.e. hyperspectral images and multimodal remote sensing datasets) are utilized for experimental analysis, and extensive experimental results have certified the progressiveness of the investigated approach. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

7. Graph convolutional network method for small sample classification of hyperspectral images

Author

ZUO Xibing, LIU Bing, YU Xuchu, ZHANG Pengqiang, GAO Kuiliang, and ZHU Enze

Subjects
Computer Science::Computer Vision and Pattern Recognition, hyperspectral image classification, graph convolutional network, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, local binary patterns, Mathematical geography. Cartography, small sample, GA1-1776
Abstract

Existing based on convolutional neural network classification method of hyperspectral images usually rules of the square area of image convolution, not widely adapt to different terrain local area distribution and geometry appearance of the image, therefore, under the condition of small sample classification performance is poorer, and figure convolution can network topology information on the map represent irregular image area of the convolution. Therefore, a hyperspectral image classification method based on graph convolution network is proposed. In this method, the spatial spectral information of the image is considered in the process of constructing the graph, and the feature information of the neighbor node is aggregated by the graph convolution network. Experimental results on three data sets, Pavia university, Indian Pines and Salinas, show that this method can achieve a high classification accuracy with a small number of training samples.

Published
2021

26. Deep 3D convolutional network combined with spatial-spectral features for hyperspectral image classification

Author

LIU Bing, YU Xuchu, ZHANG Pengqiang, and TAN Xiong

Subjects
Computer Science::Computer Vision and Pattern Recognition, hyperspectral image classification, 3D convolution, convolutional neural network, lcsh:Mathematical geography. Cartography, lcsh:GA1-1776, residual learning
Abstract

A classification method of hyperspectral images based on deep 3D convolution networks is proposed in order to deal with the high dimensional and small samples of hyperspectral image classification. The method first uses hyperspectral data cube as input, and uses 3D convolution operation to extract 3D spatial-spectral features of hyperspectral data cube. Then, the residual learning is used to construct the deep network and extract higher level feature expression to improve the classification accuracy. Finally, the Dropout regularization method is used to prevent overfitting. Experiments were conducted on the University of Pavia, Indian Pines and Salinas datasets, and the results demonstrate that compared with support vector machine and the existing deep learning classification method for hyperspectral images, the method can effectively improve the classification accuracy of hyperspectral image.

Published
2018

28. Hyperspectral image classification with deep 3D capsule network and Markov random field.

Author

Tan, Xiong, Xue, Zhixiang, Yu, Xuchu, Sun, Yifan, and Gao, Kuiliang

Subjects
HYPERSPECTRAL imaging systems, MARKOV processes, DEEP learning, IMAGE processing, THREE-dimensional imaging
Abstract

To address the existing problems of capsule networks in deep feature extraction and spatial‐spectral feature fusion of hyperspectral images, this paper proposes a hyperspectral image classification method that combines a deep residual 3D capsule network and Markov random field. Based on this method, the deep spatial‐spectral features of hyperspectral images are extracted using the deep residual 3D convolutional structure, the vector capsules of the features are obtained by the initial capsule layer and mapped into probability capsules via the 3D dynamic routing mechanism to construct the classification probability map, and the spatial structure of the classification results is regularised by the Markov random field to further improve the classification accuracy and performance of the images. Two sets of benchmark hyperspectral images, namely Indian Pines and Pavia University data sets, were used to conduct comparative experiments and ablation study. The experimental results showed that, compared with the conventional convolutional neural network and existing capsule network models, the proposed method not only improves the classification accuracy of the images but also partly eliminates the category noise and affords a more regular classification probability map. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

36. Noise reduction of hyperspectral imagery based on hypergraph laplacian regularized low-rank representation

Author

Yu Xuchu, Xue Zhixiang, and Zhou Yawen

Subjects
Hypergraph, Rank (linear algebra), Computer science, business.industry, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 0211 other engineering and technologies, Hyperspectral imaging, Pattern recognition, 02 engineering and technology, Data point, Computer Science::Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Representation (mathematics), Coefficient matrix, Laplace operator, 021101 geological & geomatics engineering
Abstract

Low-rank representation is one of the state-of-art hyperspectral image denoising algorithms, but it suffers from ignoring the high-order relationships between data points in image. In this paper, we propose a hypergraph laplacian regularized low-rank representation algorithm for noise reduction of hyperspectral images, which can represent the high-order relations between data points by using the hypergraph laplacian regularization. On the other hand, to further improve the ability to maintain the local information, the sparse and non-negative constraints have been added to the model coefficient matrix. The proposed method not only resumes the low-rank signal components, but also represents the high-order relations of the image data. The experimental results on AVIRIS and ProSpecTIR-VS datasets show that the proposed approach canbetter maintain the spatial and spectral information of images, which improves the hyperspectral image denoising results.

Published
2016

42. Small target extraction based on independent component analysis for hyperspectral imagery

Author

Lu Wei and Yu Xuchu

Subjects
Computer science, business.industry, Geography, Planning and Development, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Hyperspectral imaging, Pattern recognition, Image segmentation, Small target, Independent component analysis, Skewness, Feature (computer vision), Histogram, Kurtosis, Computer vision, Artificial intelligence, Computers in Earth Sciences, business
Abstract

A small target detection approach based on independent component analysis for hyperspectral data is put forward. In this algorithm, firstly the fast independent component analysis(FICA) is used to collect target information hided in high-dimensional data and projects them into low-dimensional space. Secondly, the feature images are selected with kurtosis. At last, small targets are extracted with histogram image segmentation which has been labeled by skewness.

Published
2006

43. A dense convolutional neural network for hyperspectral image classification.

Author

Zhi, Lu, Yu, Xuchu, Liu, Bing, and Wei, Xiangpo

Subjects
*ARTIFICIAL neural networks, *REMOTE sensing, *REMOTE-sensing images, *IMAGE processing, *ORGANIC cation transporters
Abstract

In this letter, a dense convolutional neural network (DCNN) is proposed for hyperspectral image classification, aiming to improve classification performance by promoting feature reuse and strengthening the flow of features and gradients. In the network, features are learned mainly through designed dense blocks, where feature maps generated in each layer can connect directly to the subsequent layers by a concatenation mode. Experiments are conducted on two well-known hyperspectral image data sets, using the proposed method and four comparable methods. Results demonstrate that overall accuracies of the DCNN reached 97.61 and 99.50% for the respective image data sets, representing an obvious improvement over the accuracies of the compared methods. The study confirms that the DCNN can provide more discriminable features for hyperspectral image classification and can offer higher classification accuracies and smoother classification maps. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

44. Local Hypergraph Laplacian Regularized Low-Rank Representation for Noise Reduction of Hyperspectral Images

Author

余旭初 Yu Xuchu, 谭 熊 Tan Xiong, 薛志祥 Xue Zhixiang, and 付琼莹 Fu Qiongying

Subjects
0209 industrial biotechnology, Hypergraph, business.industry, Computer science, Noise reduction, Representation (systemics), Hyperspectral imaging, Pattern recognition, 02 engineering and technology, Atomic and Molecular Physics, and Optics, Electronic, Optical and Magnetic Materials, 020901 industrial engineering & automation, 0202 electrical engineering, electronic engineering, information engineering, Rank (graph theory), 020201 artificial intelligence & image processing, Artificial intelligence, business, Laplace operator
Published
2017

47. Using of geospatial video surveillance networks for urban security and emergency applications

Author

YU Xuchu, Zhang Pengqiang, Tang Xiong, and Yu Wenshuai

Subjects
Geospatial analysis, Computer science, business.industry, Real-time computing, Cognitive neuroscience of visual object recognition, computer.software_genre, Object detection, Urban security, Remote sensing (archaeology), Computer vision, Artificial intelligence, business, computer, Change detection
Abstract

Geospatial video surveillance network (GVSN) is an effective remote sensing approach for urban security and emergency applications. In this paper, the GVSN system could be separated into four basic functional parts that include change detection, object recognition, target tracking and target positioning. Each part has its special utility to solve the security and emergency problems. When the functions applied in urban security and emergency, based on the illustration and analysis of them, the paper emphasizes the importance of the geo-information to the networks, because it enlarges the surveillance area and enhances the functions of the video networks. And according to the explanation of different security and emergency applications, it also clarifies that the extraction and operation of the target characteristics are the basics of processing algorithms.

Published
2009

Catalog

Books, media, physical & digital resources
See catalog results