Fractional Fourier Transform and Transferred CNN Based on Tensor for Hyperspectral Anomaly Detection

Zhang, Lili; Cheng, Baozhi

doi:10.1109/lgrs.2021.3072249

Cited by 20 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TCNNT can effectively utilize the spatial and spectral information of HSI. Furthermore, Zhang et al [78] proposed a fractional Fourier transform and transferred CNN based on tensor (FrFTTCNNT) for HAD. The FrFTTCNNT employs tensor transformation and PCA as the preprocessing and combines FrFT and TCNNT.…”

Section: Feature Learning-based Methodsmentioning

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

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: Feature Learning-based Methodsmentioning

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

“…11 shows the target-background separability box plots of the detection results of the MCLT and comparison methods on the four HSI data sets. In the target-background separability box plots, target and background pixels with statistically distributed values are placed in the box, removing the highest and lowest 10% of data in the target and background classes [60]. The red boxes indicate the distribution of targets, and the green boxes indicate the distribution of backgrounds.…”

Section: ) Evaluation Criterionmentioning

confidence: 99%

An Unsupervised Momentum Contrastive Learning Based Transformer Network for Hyperspectral Target Detection

Wang,

Chen,

Zhao

et al. 2024

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

View full text Add to dashboard Cite

Hyperspectral target detection plays a pivotal role in various civil and military applications. Although recent advancements in deep learning have largely embraced supervised learning approaches, they often hindered by the limited availability of labeled data. Unsupervised learning, therefore, emerges as a promising alternative, yet its potential has not been fully realized in current methodologies. This paper proposes an innovative unsupervised learning framework employing a momentum contrastive learning-based transformer network specifically tailored for hyperspectral target detection. The proposed approach innovatively combines transformer-based encoder and momentum encoder networks to enhance feature extraction capabilities, adeptly capturing both local spectral details and long-range spectral dependencies through the novel overlapping spectral patch embedding and a cross-token feedforward layer. This dual-encoder design significantly improves the model's ability to discern relevant spectral features amidst complex backgrounds. Through unsupervised momentum contrastive learning, a dynamically updated queue of negative sample features is utilized so that the model can demonstrate superior spectral discriminability. This is further bolstered by a unique background suppression mechanism leveraging nonlinear transformations of cosine similarity detection results, with two nonlinearly pull-up operations, significantly enhancing target detection sensitivity, where the nonlinearly operations are the exponential function with its normalization and the power function with its normalization, respectively. Comparative analysis against seven state-of-the-art hyperspectral target detection methods across four real hyperspectral images demonstrates the effectiveness of the proposed method for hyperspectral target detection, with an increase in detection accuracy and a competitive computational efficiency. An extensive ablation study further validates the critical components of the proposed framework, confirming its comprehensive capability and applicability in hyperspectral target detection scenarios.

show abstract

“…In order to restore input data to the original spectrums, the proposed FTSGAN needs to learn the embedded features and mapping relationship of the inverse fractional Fourier transform (FrFT) instead of focussing on maintaining numerical equivalence between the input and output data, hence we innovatively convert the reconstruction task into a mapping task for HAD. Because FrFT aptly demonstrates remarkable power in noise suppression and spectral band decorrelation and enhances the separability of backgrounds and anomalies in the FrFD [48][49][50] (including frequency domain information), we select FrFT for the task of mapping network learning. On the premise that FTSGAN can map and restore the background input data from the FrFD back to the original spectral domain as far as possible, and make full use of the differences of the depth feature between backgrounds and anomalies in the FrFD, thus amplifying the anomalous characteristics of anomalies and hindering the restoration of the anomaly pixels.…”

Section: Introductionmentioning

confidence: 99%

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Wang

Gao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Most unsupervised or semisupervised hyperspectral anomaly detection (HAD) methods train background reconstruction models in the original spectral domain. However, due to the noise and spatial resolution limitations, there may be a lack of discrimination between backgrounds and anomalies. This makes it easy for the autoencoder to capture the low‐level features shared between the two, thereby increasing the difficulty of separating anomalies from the backgrounds, which runs counter to the purpose of HAD. To this end, the authors map the original spectrums to the fractional Fourier domain (FrFD) and reformulate it as a mapping task in which restoration errors are employed to distinguish background and anomaly. This study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for HAD. Specifically, the depth separable features of backgrounds and anomalies are enhanced in the FrFD. Due to the semisupervised approach, FTSGAN needs to learn the embedded features of the backgrounds, thus mapping and restoring them from the FrFD to the original spectral domain. This strategy effectively prevents the model from focussing on the numerical equivalence of input and output, and restricts the ability of FTSGAN to restore anomalies. The comparison and analysis of the experiments verify that the proposed method is competitive.

show abstract

Fractional Fourier Transform and Transferred CNN Based on Tensor for Hyperspectral Anomaly Detection

Cited by 20 publications

References 24 publications

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

Hyperspectral Anomaly Detection Based on Machine Learning: An Overview

An Unsupervised Momentum Contrastive Learning Based Transformer Network for Hyperspectral Target Detection

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Contact Info

Product

Resources

About