Kernel-Based Nonlinear Anomaly Detection via Union Dictionary for Hyperspectral Images

Gao, Yenan; Gu, Jiafeng; Cheng, Tongkai; Wang, Bin

doi:10.1109/tgrs.2021.3093591

Cited by 7 publications

(11 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robust nonlinear anomaly detector [33] combines the kernelization procedure and robust iterative background distribution estimation strategy to formulate a nonlinear and robust detector, which can effectively estimate the background distribution and avoid contamination to a certain extent. The kernel-based nonlinear anomaly detection method via union dictionary [34] considers the nonlinear mixing models to demonstrate the intrinsic nonlinear characteristics of the real HSIs. A union dictionary comprising a background and anomalous atoms is also constructed by considering the local spatial correlations and global anomalies.…”

Section: Traditional Machine Learning-based Models a Feature Mapping-...mentioning

confidence: 99%

“…Yang et al [26] proposed a low-rank and sparse matrix decomposition with OSP-based background suppression and adaptive weighting for HAD. The OSP is employed to project the sparse component into the background orthogonal CRD [17] SSSAE [55] SR-LMM [43] PAB-DC [44] KIFD [86] PTA [90] KNUD [34] MCAEN [47] BASO [29] Transfer CNND [76] SAAD [60] SSFE [82] SAFL [64] HADGAN [72] Auto-AD [73] EDLAD [62] RGAE [75] Traditional Machine Learning Methods Deep Learning Methods subspace that is estimated from the low-rank component to suppress the background interferences and highlight the anomalies. Chang et al [27] presents an OSP version of go decomposition (OSP-GoDec), which implements GoDec in an iterative process by a sequence of OSPs to find desired lowrank and sparse matrices.…”

Section: Traditional Machine Learning-based Models a Feature Mapping-...mentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral anomaly detection (HAD) is an important hyperspectral image application. HAD can find pixels with anomalous spectral signatures compared with their neighbor background without any prior information. While most of the existed researches related to statistic-based and distance-based techniques by summarizing the background samples with certain models and then finding the very few outliers by various of distance metrics, this review focuses on the HAD based on machine learning methods, which have witnessed remarkable progress in the recent years. In particular, these studies can generally be roughly grouped into the traditional machine learning and deep learning-based methods. Several representative HAD methods, including both traditional machine and deep learning-based methods, are then conducted on four real HSIs in the experiments. Finally, conclusions regarding HAD are summarized, and prospects and future development direction are discussed.

show abstract

Section: Traditional Machine Learning-based Models a Feature Mapping-...mentioning

confidence: 99%

Section: Traditional Machine Learning-based Models a Feature Mapping-...mentioning

confidence: 99%

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…4) Comparison of Detection Results: Here, we compare the detection performance of the proposed KDM-TVS with other anomaly detectors by utilizing the synthetic data set. The competitors include the linear detectors (LRX [8], CRD [12], TVSDM [18], LSC-TV [19]), and the nonlinear detectors (KRX [26], KCRD [12], KNUD [30], KIFD [27]). LRX and KRX are two improved versions of RX, which are recognized as the benchmarks among the statistical approaches.…”

Section: A Experiments On Synthetic Data Setmentioning

confidence: 99%

“…in LRX [8], CRD [12], KCRD [12] and KNUD [30] are all set to (3,9). The tradeoff parameter λ in CRD and KCRD is set to 6 10as recommended in [12].…”

Section: A Experiments On Synthetic Data Setmentioning

confidence: 99%

“…In terms of this issue, the KHype [29] proposes the endmember-kernel theory to realize the nonlinear interactions between endmembers. On this basis, the KNUD [30] utilizes the endmember-kernel theory with dual window to implement the anomaly detection. However, the detection result of KNUD is affected to some extent due to the absent of the global spatial properties, and the deficiency of the dual window has still not been solved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kernel-Based Decomposition Model With Total Variation and Sparsity Regularizations via Union Dictionary for Nonlinear Hyperspectral Anomaly Detection

Wang

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Many linear approaches have been extensivelyproposed for the anomaly detection problem in hyperspectral images (HSIs), while nonlinear approaches have been rarely studied although most practical cases are nonlinear. Moreover, these existing nonlinear methods simply nonlinearly map each pixel into a high-dimensional space, which does not describe complex light scattering effects between endmembers. To address the above issues, this paper proposes an endmember-kernel-based decomposition model with total variation and sparsity regularizations via union dictionary for the nonlinear anomaly detection in HSIs. The proposed decomposition model utilizes endmember-kernel theory to handle nonlinear interactions between atoms in the dictionary, allowing for effective characterization of complex light scattering effects. By using this endmember-kernel-based decomposition model, a hyperspectral imagery can be decomposed into three components: anomaly, background, and noise. To separate these components effectively, the total variation (TV) and sparsity regularizations are incorporated into the decomposition model to characterize the spatial properties of the background and the anomaly, respectively. Besides, we present a novel construction framework of union dictionary that combines superpixel segmentation and clustering methods sequentially to achieve more accurate dictionary representation capabilities. Finally, the anomalous level of a tested pixel is calculated by the abundances associated with the anomaly dictionary. The experimental results on both synthetic and real hyperspectral data sets demonstrate that the proposed method outperforms several linear and nonlinear state-of-the-art anomaly detectors.

show abstract

Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation

Zhang

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Kernel-Based Nonlinear Anomaly Detection via Union Dictionary for Hyperspectral Images

Cited by 7 publications

References 55 publications

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Kernel-Based Decomposition Model With Total Variation and Sparsity Regularizations via Union Dictionary for Nonlinear Hyperspectral Anomaly Detection

Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation

Contact Info

Product

Resources

About