Robust deflated principal component analysis via multiple instance factorings for dimension reduction in remote sensing images

被引:2
作者
Ganaa, Ernest Domanaanmwi [1 ,2 ]
Abeo, Timothy Apasiba [3 ]
Wang, Liangjun [1 ]
Song, He-Ping [1 ]
Shen, Xiang-Jun [1 ,4 ]
机构
[1] Jiangsu Univ, Sch Comp Sci & Commun Engn, Zhenjiang, Jiangsu, Peoples R China
[2] Wa Polytech, Sch Appl Sci & Technol, Wa, Ghana
[3] Tamale Tech Univ, Sch Appl Sci, Tamale, Ghana
[4] Jiangsu Univ, Jingkou New Generat Informat Technol Ind Inst, Zhenjiang, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
dimension reduction; deflation; principal component analysis; instance factorings; remote sensing; FEATURE-EXTRACTION; FEATURE-SELECTION; NOISE ESTIMATION; PCA; CLASSIFICATION;
D O I
10.1117/1.JRS.14.032608
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Remote sensing data are often adversely affected by noises due to atmospheric water absorption, transmission errors, sensor sensitivity, and saturation. Therefore, the performance of the classical principal component analysis (PCA) is negatively affected when dealing with such noisy data. To overcome this problem, a robust deflated PCA via multiple instance factorings (RDPCA-MIF) for dimension reduction in remote sensing images is proposed. In contrast to the traditional PCA, a penalty is imposed on the instance space through instance factoring technique to suppress the effect of noise in pursuing projections. To achieve this, we use two strategies, total distance, and cosine similarity metrics. Both strategies discriminate between noise and authentic data points by iteratively learning the relationship between instances and projections. Moreover, a deflation strategy that enables multiple relationships learning between instances and projections is applied to thoroughly evaluate the importance of instances in relation to all projections. Extensive experimental evaluations of the proposed RDPCA-MIF on Salinas-A dataset and shallow and deep features from the NWPU-RESISC45 remote sensing dataset prove its superiority over six comparative methods in dimension reduction and classification tasks. (C) 2020 Society of Photo Optical Instrumentation Engineers (SPIE)
引用
收藏
页数:16
相关论文
共 50 条
[41]   Superpixel-based principal component analysis for high resolution remote sensing image classification [J].
Su, Tengfei .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (23) :34173-34191
[42]   Superpixel-based principal component analysis for high resolution remote sensing image classification [J].
Tengfei Su .
Multimedia Tools and Applications, 2019, 78 :34173-34191
[43]   Kernel Principal Component Analysis for the Classification of Hyperspectral Remote Sensing Data over Urban Areas [J].
Fauvel, Mathieu ;
Chanussot, Jocelyn ;
Benediktsson, Jon Atli .
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2009,
[44]   Optimization of correlated multiple quality characteristics robust design using principal component analysis [J].
Wu, FC ;
Chyu, CC .
JOURNAL OF MANUFACTURING SYSTEMS, 2004, 23 (02) :134-143
[45]   Saliency Analysis via Hyperparameter Sparse Representation and Energy Distribution Optimization for Remote Sensing Images [J].
Zhang, Libao ;
Lv, Xinran ;
Liang, Xu .
REMOTE SENSING, 2017, 9 (06)
[46]   Tensor Ring Discriminant Analysis Used for Dimension Reduction of Remote Sensing Feature Tensor [J].
Gao, Tong ;
Gu, Lingjia ;
Chen, Hao .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
[47]   Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition [J].
Fang, Shun ;
Xu, Zhengqin ;
Wu, Shiqian ;
Xie, Shoulie .
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, :1348-1357
[48]   Discrete Robust Principal Component Analysis via Binary Weights Self-Learning [J].
Nie, Feiping ;
Wang, Sisi ;
Wang, Zheng ;
Wang, Rong ;
Li, Xuelong .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (11) :9064-9077
[49]   Fast and provable tensor robust principal component analysis via scaled gradient descent [J].
Dong, Harry ;
Tong, Tian ;
Ma, Cong ;
Chi, Yuejie .
INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2023, 12 (03)
[50]   A High Precision Parallel Principal Skewness Analysis Algorithm and Its Application to Remote Sensing Images [J].
Wang, Dahu ;
Liu, Chang ;
Wang, Jian ;
Yao, Kai ;
Zhang, Zhen .
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2023, 45 (10) :S492-S501