Article
Environmental Sciences
Zixian Ge, Guo Cao, Youqiang Zhang, Hao Shi, Yanbo Liu, Ayesha Shafique, Peng Fu
Summary: This paper investigates the issues of multiscale information and feature fusion in hyperspectral image classification and proposes an adaptive attention constraint fusion module and a semantic feature enhancement module. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Bing Tu, Qi Ren, Qianming Li, Wangquan He, Wei He
Summary: This article proposes a superpixel-pixel-subpixel multilevel (SPSM) network to address the challenge of identifying irregular ground cover in hyperspectral images. The network utilizes a graph convolutional network (GCN) to simulate superpixel features and a global attention module (GAM) to learn pixel-level features. Additionally, a normalized attention module (NAM) is used to enhance material discrimination. The three features are then fused to improve classification robustness and target recognition.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Geochemistry & Geophysics
Yuan Fang, Yuxian Wang, Linlin Xu, Yujia Chen, Alexander Wong, David A. Clausi
Summary: This article proposes a Bayesian neural network for unsupervised subpixel mapping, which integrates different prior information and model constraints to achieve more accurate and visual results compared to other state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Remote Sensing
Peng Wang, Zhongchen He, Cai Li, Shuaipeng Ye, Kun Wang, Jiale Zhao
Summary: This paper proposes a new interpolation sub-pixel mapping model MSSI-PSF, which improves the quality of coarse fractional images by considering the PSF effect and achieves better mapping results using a class allocation method.
REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
Haimiao Ge, Liguo Wang, Moqi Liu, Xiaoyu Zhao, Yuexia Zhu, Haizhu Pan, Yanzhong Liu
Summary: This article proposes a pyramidal multiscale spectral-spatial convolutional network with polarized self-attention for pixel-wise HSI classification. The network consists of three stages: channel-wise feature extraction network, spatial-wise feature extraction network, and classification network. Experimental results demonstrate that the proposed network outperforms other related methods on several public HSI datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Renwei Dian, Shutao Li, Xudong Kang
Summary: This article introduces a novel HSI and MSI fusion method, combining subspace representation and CNN denoiser, trained on gray images and directly applicable to any HSI and MSI datasets for superior performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Geochemistry & Geophysics
Lin He, Jinhua Xie, Jun Li, Antonio Plaza, Jocelyn Chanussot, Jiawei Zhu
Summary: In this paper, a VSPC-CNN method is proposed for arbitrary resolution HS pansharpening. The method consists of two-stage elevators to improve the resolution of the input HS image and adjust it to arbitrary resolutions. Experimental results show the superiority of the proposed method on both simulated and real datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Linzhou Yu, Jiangtao Peng, Na Chen, Weiwei Sun, Qian Du
Summary: This paper proposes a novel two-branch deeper graph convolutional network (TBDGCN) to extract both superpixel and pixel-level features for hyperspectral image classification. The TBDGCN model addresses the oversmoothing and overfitting problems by using the DropEdge technique and residual connection in the GCN branch, and captures attention-based spectral-spatial features through a mixed attention mechanism in the CNN branch. The features from both branches are fused for classification.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Feng Zhao, Junjie Zhang, Zhe Meng, Hanqiang Liu
Summary: A densely connected pyramidal dilated convolutional network (PDCNet) is proposed in this paper to address the issue of blind spots in the receptive field caused by dilated convolution, achieving continuous and multi-scale receptive fields. By utilizing a pyramid pattern of dilated convolutional layers and a feature fusion mechanism, the network demonstrates good classification performance in HSI compared to other popular models.
Article
Geochemistry & Geophysics
Qichao Liu, Liang Xiao, Jingxiang Yang, Zhihui Wei
Summary: This paper proposes a heterogeneous deep network called CEGCN, which integrates CNN and GCN branches for feature learning on different scales of image regions to generate complementary spectral-spatial features. By integrating the graph encoding process into the network and learning edge weights from training data, it promotes node feature learning and makes the graph more adaptive to HSI content.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Lingbo Huang, Yushi Chen, Xin He, Pedram Ghamisi
Summary: This study investigates contrastive learning as a pre-training strategy for hyperspectral image classification, proposing a supervised contrastive learning framework and three techniques to enhance generalization in the case of limited training samples. Experimental results show that the proposed methods provide competitive classification accuracy compared to the state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Yao Li, Chengming Ye, Yonggang Ge, Jose Marcato Junior, Wesley Nunes Goncalvese, Jonathan Li
Summary: In this study, a new method using deep convolutional neural network called CNNP is proposed for identifying building rooftops materials based on hyperspectral remote sensing imagery. By extracting features using PPI constraints and different convolutional kernel sizes, the method achieves high accuracy and provides an innovative idea for remote sensing image classification.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Review
Engineering, Electrical & Electronic
Ajay Sharma, Bhavana P. Shrivastava
Summary: This article provides a comprehensive study of image superresolution (SR) using a deep convolution neural network (CNN). It explores different network designs and compares their performances and complexity. It also highlights the importance of upscaling techniques and loss functions in reconstruction performance and presents an analysis of standard datasets to inform network design. The article identifies shortcomings in existing models and suggests future research directions for image SR.
IEEE SENSORS JOURNAL
(2023)
Article
Environmental Sciences
Jiaqing Zhang, Jie Lei, Weiying Xie, Daixun Li
Summary: The fusion of hyperspectral and LiDAR images is crucial for accurate classification and recognition in remote sensing. This study proposes a method that combines a binary convolutional neural network and a graph convolutional network with invariant attributes to overcome the challenges of constructing effective graph structures. The method utilizes a joint detection framework to simultaneously learn features from regular and irregular regions, resulting in an enhanced structural representation of the images. Experimental results demonstrate the superior performance of the proposed method in hyperspectral image analysis tasks.
Article
Geochemistry & Geophysics
Huapeng Wu, Jie Gui, Yang Xu, Zebin Wu, Yuan Yan Tang, Zhihui Wei
Summary: In this article, an efficient cross-modality self-calibrated network (CMSCN) is proposed for hyperspectral and multispectral image fusion. By combining a cross-modality nonlocal module and a cross-scale self-calibrated convolution structure, the learning ability of the model is improved. The introduced efficient spatial-spectral attention mechanism provides more accurate information for hyperspectral image reconstruction. Experimental results demonstrate the superiority of the proposed method over other image fusion methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)