1
|
Zhao Y, Zai C, Hu N, Shi L, Zhou X, Sun J. Adaptive pixel attention network for hyperspectral image classification. Sci Rep 2024; 14:29079. [PMID: 39580519 PMCID: PMC11585658 DOI: 10.1038/s41598-024-73988-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2024] [Accepted: 09/23/2024] [Indexed: 11/25/2024] Open
Abstract
Patch features obtained by fixed convolution kernel have become the main form in hyperspectral image (HSI) classification processing. However, the fixed convolution kernel limits the weight learning of channels, which results in the potential connections between pixels not being captured in patches, and seriously affects the classification performance. To tackle the above issues, we propose a novel Adaptive Pixel Attention Network, which can improve HSI classification by further mining the connections between pixels in patch features. Specifically, a Spectral-Spatial Superposition Enhancement module is first proposed for enhancing the spectral-spatial information of 3D input cubes via complementing the 1D spectral vectors by zero and reflection filling operations. More importantly, we also propose a new Adaptive Pixel Attention mechanism, which explores Cosine and Euclidean similarity to adaptively explore the distance and angle relationship between pixels of different scale convolution patch features. Moreover, the Cross-Layer Information Complement module is designed to form a contextual interaction by integrating the output features of different convolution layers, which can prevent the omission of discriminative information and further improve the network performance. Experimental results on four widely used HSI datasets IP, UP, HU, and KSC show that the proposed network is superior to other state-of-the-art classification models in accuracy, and it also has a better efficiency than other 3D works.
Collapse
Affiliation(s)
- Yuefeng Zhao
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Chengmin Zai
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Nannan Hu
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China.
| | - Lu Shi
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Xue Zhou
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| | - Jingqi Sun
- Shandong Provincial Engineering and Technical Center of Light Manipulation, Shandong Provincial Key Laboratory of Optics and Photonic Devices, School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China
| |
Collapse
|
2
|
Kavran D, Mongus D, Žalik B, Lukač N. Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery. SENSORS (BASEL, SWITZERLAND) 2023; 23:6648. [PMID: 37514942 PMCID: PMC10384354 DOI: 10.3390/s23146648] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 07/14/2023] [Accepted: 07/19/2023] [Indexed: 07/30/2023]
Abstract
Multispectral satellite imagery offers a new perspective for spatial modelling, change detection and land cover classification. The increased demand for accurate classification of geographically diverse regions led to advances in object-based methods. A novel spatiotemporal method is presented for object-based land cover classification of satellite imagery using a Graph Neural Network. This paper introduces innovative representation of sequential satellite images as a directed graph by connecting segmented land region through time. The method's novel modular node classification pipeline utilises the Convolutional Neural Network as a multispectral image feature extraction network, and the Graph Neural Network as a node classification model. To evaluate the performance of the proposed method, we utilised EfficientNetV2-S for feature extraction and the GraphSAGE algorithm with Long Short-Term Memory aggregation for node classification. This innovative application on Sentinel-2 L2A imagery produced complete 4-year intermonthly land cover classification maps for two regions: Graz in Austria, and the region of Portorož, Izola and Koper in Slovenia. The regions were classified with Corine Land Cover classes. In the level 2 classification of the Graz region, the method outperformed the state-of-the-art UNet model, achieving an average F1-score of 0.841 and an accuracy of 0.831, as opposed to UNet's 0.824 and 0.818, respectively. Similarly, the method demonstrated superior performance over UNet in both regions under the level 1 classification, which contains fewer classes. Individual classes have been classified with accuracies up to 99.17%.
Collapse
Affiliation(s)
- Domen Kavran
- Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroška Cesta 46, 2000 Maribor, Slovenia
| | - Domen Mongus
- Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroška Cesta 46, 2000 Maribor, Slovenia
| | - Borut Žalik
- Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroška Cesta 46, 2000 Maribor, Slovenia
| | - Niko Lukač
- Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroška Cesta 46, 2000 Maribor, Slovenia
| |
Collapse
|
3
|
Yan C, Fan X, Fan J, Yu L, Wang N, Chen L, Li X. HyFormer: Hybrid Transformer and CNN for Pixel-Level Multispectral Image Land Cover Classification. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:3059. [PMID: 36833777 PMCID: PMC9967485 DOI: 10.3390/ijerph20043059] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/31/2022] [Revised: 02/07/2023] [Accepted: 02/08/2023] [Indexed: 06/18/2023]
Abstract
To effectively solve the problems that most convolutional neural networks cannot be applied to the pixelwise input in remote sensing (RS) classification and cannot adequately represent the spectral sequence information, we propose a new multispectral RS image classification framework called HyFormer based on Transformer. First, a network framework combining a fully connected layer (FC) and convolutional neural network (CNN) is designed, and the 1D pixelwise spectral sequences obtained from the fully connected layers are reshaped into a 3D spectral feature matrix for the input of CNN, which enhances the dimensionality of the features through FC as well as increasing the feature expressiveness, and can solve the problem that 2D CNN cannot achieve pixel-level classification. Secondly, the features of the three levels of CNN are extracted and combined with the linearly transformed spectral information to enhance the information expression capability, and also used as the input of the transformer encoder to improve the features of CNN using the powerful global modelling capability of the Transformer, and finally the skip connection of the adjacent encoders to enhance the fusion between different levels of information. The pixel classification results are obtained by MLP Head. In this paper, we mainly focus on the feature distribution in the eastern part of Changxing County and the central part of Nanxun District, Zhejiang Province, and conduct experiments based on Sentinel-2 multispectral RS images. The experimental results show that the overall accuracy of HyFormer for the study area classification in Changxing County is 95.37% and that of Transformer (ViT) is 94.15%. The experimental results show that the overall accuracy of HyFormer for the study area classification in Nanxun District is 95.4% and that of Transformer (ViT) is 94.69%, and the performance of HyFormer on the Sentinel-2 dataset is better than that of the Transformer.
Collapse
Affiliation(s)
- Chuan Yan
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Xiangsuo Fan
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
- Guangxi Collaborative Innovation Centre for Earthmoving Machinery, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Jinlong Fan
- National Satellite Meteorological Center, China Meteorological Administration, Beijing 100081, China
| | - Ling Yu
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Nayi Wang
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Lin Chen
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Xuyang Li
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| |
Collapse
|
4
|
Chuang TY, Zhang XD, Chen CK. Estimating the Roll Angle for a Two-Wheeled Single-Track Vehicle Using a Kalman Filter. SENSORS (BASEL, SWITZERLAND) 2022; 22:8991. [PMID: 36433586 PMCID: PMC9694013 DOI: 10.3390/s22228991] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Revised: 11/10/2022] [Accepted: 11/15/2022] [Indexed: 06/16/2023]
Abstract
This study determines the roll angle for a two-wheeled single-track vehicle during cornering. The kinematics are analyzed by coordinate transformation to determine the relationship between the measured acceleration and the acceleration in the global coordinate. For a measurement error or noise, the state space expression is derived. Using the theory for a Kalman filter, an estimator with two-step measurement updates estimates the yaw rate and roll angle using the acceleration and angular velocity signals from an IMU sensor. A bicycle with relevant electronic products is used as the experimental object for a steady turn, a double lane change and a sine wave turn in real time to determine the effectiveness of the estimator. The results show that the proposed estimator features perfect reliability and accuracy and properly estimates the roll angle for a two-wheeled vehicle using IMU and velocity.
Collapse
Affiliation(s)
- Tzu-Yi Chuang
- Department of Vehicle Engineering, National Taipei University of Technology, Taipei 10608, Taiwan
| | - Xiao-Dong Zhang
- Department of Vehicle Engineering, National Taipei University of Technology, Taipei 10608, Taiwan
- School of Information and Mechatronics Engineering, Ningde Normal University, Ningde 352100, China
| | - Chih-Keng Chen
- Department of Vehicle Engineering, National Taipei University of Technology, Taipei 10608, Taiwan
| |
Collapse
|
5
|
Kang X, Li X, Yao H, Li D, Jiang B, Peng X, Wu T, Qi S, Dong L. Dynamic hypergraph neural networks based on key hyperedges. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2022.10.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
6
|
Peng M, Juan X, Li Z. Graph prototypical contrastive learning. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2022.09.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
7
|
Ding Y, Zhang Z, Zhao X, Hong D, Cai W, Yu C, Yang N, Cai W. Multi-feature fusion: Graph neural network and CNN combining for hyperspectral image classification. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.06.031] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|