Yule Duan
ABSTRACT
Collaborative representation (CR) based graph embedding has been widely used for dimensionality reduction of remotely sensed hyperspectral images because CR is able to reveal the structure of high-dimensional data adaptively. However, CR denotes a data point as a linear combination of global data while ignoring the important structure shared by the nearby samples. To solve this problem, a local structure-aware collaborative graph embedding (LSaCGE) method is proposed to preserve both local structure and collaborative relationship in the embedding process. In this method, a local structure-aware CR model is first designed by introducing the neighbor point aware and neighborhood set aware items into CR, which aims to be aware of the local structure during the process of representation. With the representation coefficients, two collaborative structure preservation graphs that reveal the discriminative collaborative relationship and local structure are constructed to achieve the final embedding process. The experimental results show that the performance of our method on two public HSI data sets outstand that of several state-of-the-art methods.
- Zengfu Hou, Wei Li, Lu Li, Ran Tao, and Qian Du. 2021. Hyperspectral change detection based on multiple morphological profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-12. https://doi.org/10.1109/TGRS.2021.3090802Google Scholar
Cross Ref
- Ye, Zhen, Wang, Jie, and Bai, Lin. 2023. Multi-Scale Spatial-Spectral Feature Extraction Based on Dilated Convolution for Hyperspectral Image Classification[C]. 2023 6th International Conference on Image and Graphics Processing (ICIGP). 2023: 97-103. https://doi.org/10.1145/3582649.3582681Google ScholarDigital Library
- Fulin Luo, Zehua Zou, Jiamin Liu, and Zhiping Lin. 2021. Dimensionality reduction and classification of hyperspectral image via multistructure unified discriminative embedding[J]. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-16. https://doi.org/10.1109/TGRS.2021.3128764Google ScholarCross Ref
- Junran Chen, Phillip Kollmeyer, Fei Chiang, and Ali Emadi. 2023. Lithium-ion Battery State-of-Health Estimation via Histogram Data, Principal Component Analysis, and Machine Learning[C]. IEEE Transportation Electrification Conference & Expo (ITEC). IEEE, 1-6. https://doi.org/10.1109/ITEC55900.2023.10187012Google ScholarCross Ref
- Zhengying Li, Hong Huang, Zhen Zhang.2020. Deep manifold reconstruction neural network for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 19: 1-5. https://doi.org/10.1109/LGRS.2020.3042999Google ScholarCross Ref
- Jia Feng and Junping Zhang. 2020. Unsupervised feature extraction in hyperspectral image based on improved neighborhood preserving embedding[C]//IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. IEEE: 1291-1294. https://doi.org/10.1109/IGARSS39084.2020.9323526Google ScholarCross Ref
- Lin He, Xianjun Chen, Xiaofeng Xie, and Haokun Luo. 2020. Adaptive locality preserving projection for hyperspectral image classification[C]. MIPPR 2019: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications. SPIE, 11432: 8-14. https://doi.org/10.1117/12.2535915Google ScholarCross Ref
- Guangyao Shi, Hong Huang, and Lihua Wang. 2019. Unsupervised dimensionality reduction for hyperspectral imagery via local geometric structure feature learning[J]. IEEE Geoscience and Remote Sensing Letters, 17(8): 1425-1429. https://doi.org/10.1109/LGRS.2019.2944970Google ScholarCross Ref
- Luciano C. Ayres, Sergio J. M. de Almeida, Jose C. M. Bermudez, Ricardo A. Borsoi. 2021. A homogeneity-based multiscale hyperspectral image representation for sparse spectral unmixing[C]. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE,: 1460-1464. https://doi.org/10.1109/ICASSP39728.2021.9415024Google ScholarCross Ref
- Lishan Qiao, Songcan Chen, Xiaoyang Tan. 2010. Sparsity preserving projections with applications to face recognition[J]. Pattern recognition, 43(1): 331-341. https://doi.org/10.1016/j.patcog.2009.05.005Google ScholarDigital Library
- Lei Pan, Hengchao Li, Yangjun Deng, Fan Zhang, Xiangdong Chen, Qian Du. 2017. Hyperspectral dimensionality reduction by tensor sparse and low-rank graph-based discriminant analysis[J]. Remote Sensing, 9(5): 452. https://doi.org/10.3390/rs9050452Google ScholarCross Ref
- Na Liu, Wei Li, and Qian Du. 2018. Unsupervised feature extraction for hyperspectral imagery using collaboration-competition graph[J]. IEEE Journal of Selected Topics in Signal Processing, 12(6): 1491-1503. https://doi.org/10.1109/JSTSP.2018.2877474Google ScholarCross Ref
- Nam Hoai Ly, Qian Du, James E. Fowler. 2014. Collaborative graph-based discriminant analysis for hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2688-2696. https://doi.org/10.1109/JSTARS.2014.2315786Google ScholarCross Ref
- Edisanter Lo. 2019. Target Detection Algorithms in Hyperspectral Imaging Based on Discriminant Analysis[J]. Journal of Image and Graphics, 7(4):140-144, December 2019. https://doi.org/10.18178/joig.7.4.140-144Google ScholarCross Ref
Index Terms
- Dimensionality Reduction via Local Structure-Aware Collaborative Graph Embedding for Hyperspectral Remote Sensing Image
Recommendations
Discriminative globality and locality preserving graph embedding for dimensionality reduction
Highlights- Propose the DGLPGE method.
- Design new local and global graph constructions.
AbstractGraph embedding in dimensionality reduction has attracted much attention in the high-dimensional data analysis. Graph construction in graph embedding plays an important role in the quality of dimensionality reduction. However, the ...
Dimensionality reduction by collaborative preserving Fisher discriminant analysis
Highlights- Our proposed L1CPFDA/L2CPFDA can not only preserve the collaborative reconstruction relationship of the data, but also hold the strong discriminant power as ...
AbstractSparse representation-based classifier (SRC) and collaborative representation-based classifier (CRC) are two commonly used classifiers. There has been pointed out that the utilization of all the training samples in representing a query ...
Locality preserving projection with symmetric graph embedding for unsupervised dimensionality reduction
Highlights- LPP_SGE is a new unsupervised projection and symmetric graph joint learning framework.
AbstractPreserving the intrinsic structure of data is very important for unsupervised dimensionality reduction. For structure preserving, graph embedding technique is widely considered. However, most of the existing unsupervised graph ...
Comments