Image-Derived Prediction of Spectral Image Utility for Target Detection Applications

Stefanou, M.S.; Kerekes, John P.

doi:10.1109/tgrs.2009.2034295

Cited by 34 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral image cube is a collection of images of a particular scene captured across various wavelength regions in the electromagnetic spectrum. The main applications of Hyperspectral image processing is in remote sensing applications [1] [2] [3][4] such as object detection, pollution monitoring, target detection in military applicationsetc. Apart from many useful applications, HSI processing is quite challenging because HSIs are huge.…”

Section: Introductionmentioning

confidence: 99%

Data Adaptable Sparse Reconstruction for Hyperspectral Image Recovery from Compressed Measurements

K S*,

Prasantha

2020

IJITEE

View full text Add to dashboard Cite

Hyperspectral image compression using compressive sensing technique is very much important in the area of satellite image compression because it can greatly en hance the compression rate. The research work proposes a novel data adaptable sparse reconstruction algorithm for the reconstruction of hyperspectral images from compressive sensing measurements. In the proposed algorithm, compressive sensing technique is used for the compression of HSIs, where Gaussian i.i.d. matrix is used to generate compressive sensing measurements. The algorithm solves the optimization problem containing total variation regularization and data adaptable parameter terms. The regularization terms are added to provide hyperspectral data characteristics as priors into the objective function. The addition of priors helps in convergence of the algorithm into the desired solution. The algorithm alternatively reconstructs the end member matrix and abundance matrix instead of reconstructing the entire HSI at once, thereby reducing the computational complexity at the reconstruction process. To nullify the effect of modelling errors, debiasing is performed

show abstract

Section: Introductionmentioning

confidence: 99%

Data Adaptable Sparse Reconstruction for Hyperspectral Image Recovery from Compressed Measurements

K S*,

Prasantha

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…Each pixel of HSI contains a continuous spectrum with hundreds or even thousands of spectral bands, of which the width of each band is about 5-10 nm, to detect and characterize target of interest in the scene [1,2]. Target detection is one of the most wide applications of hyperspectral image processing, and it plays an important role in the real world, such as detecting humanmade objects in reconnaissance applications, searching rare minerals in geology, and researching environmental pollution [3][4][5]. Based on specific spectral signatures (prior information), the purpose of target detection is to decide whether a target of interest is present or not present (background) in a pixel-under-test, which can be viewed as a binary classifier [6,7].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Target Detection via Adaptive Information—Theoretic Metric Learning with Local Constraints

Dong

Zhang

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

By using the high spectral resolution, hyperspectral images (HSIs) provide significant information for target detection, which is of great interest in HSI processing. However, most classical target detection methods may only perform well based on certain assumptions. Simultaneously, using limited numbers of target samples and preserving the discriminative information is also a challenging problem in hyperspectral target detection. To overcome these shortcomings, this paper proposes a novel adaptive information-theoretic metric learning with local constraints (ITML-ALC) for hyperspectral target detection. The proposed method firstly uses the information-theoretic metric learning (ITML) method as the objective function for learning a Mahalanobis distance to separate similar and dissimilar point-pairs without certain assumptions, needing fewer adjusted parameters. Then, adaptively local constraints are applied to shrink the distances between samples of similar pairs and expand the distances between samples of dissimilar pairs. Finally, target detection decision can be made by considering both the threshold and the changes between the distances before and after metric learning. Experimental results demonstrate that the proposed method can obviously separate target samples from background ones and outperform both the state-of-the-art target detection algorithms and the other classical metric learning methods.

show abstract

“…Due to its rich information in the spectral dimension, hyperspectral imagery (HSI) has drawn more and more attention in the field of remote sensing [1][2][3][4][5]. Target detection aims to discriminate the specific target pixels from various of backgrounds, which is one of the most significant applications in HSI [6,7] processing. In most cases, the a priori information about the spectrum of the target of interest is difficult to obtain, so the target detection technique with no a priori information, known as anomaly detection, is widely used in practical situations [4,8,9].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Anomaly Detection via Background Estimation and Adaptive Weighted Sparse Representation

Zhu

Wen

2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Anomaly detection is an important task in hyperspectral imagery (HSI) processing. It provides a new way to find targets that have significant spectral differences from the majority of the dataset. Recently, the representation-based methods have been proposed for detecting anomaly targets in HSIs. It is essential for this type of method to construct a valid background dictionary to distinguish anomaly and background accurately. In this paper, a novel hyperspectral anomaly detection method based on background estimation and adaptive weighted sparse representation has been proposed. Firstly, to obtain the effective background dictionary without anomaly information, a new background dictionary construction strategy is designed. Secondly, the sparse representation based on the constructed background dictionary is utilized on the dataset. Anomalies and background are distinguished through the response of the residual matrix. Thirdly, the residual matrix is weighted adaptively from global and local domains, which makes anomalies and background more discriminative. An important advantage of the proposed method is that it considers the properties of anomalies in both spectral and spatial domains. Experiments on three HSI datasets reveal that our proposed method achieves an outstanding detection performance compared with the other anomaly detection algorithms.

show abstract

Image-Derived Prediction of Spectral Image Utility for Target Detection Applications

Cited by 34 publications

References 9 publications

Data Adaptable Sparse Reconstruction for Hyperspectral Image Recovery from Compressed Measurements

Data Adaptable Sparse Reconstruction for Hyperspectral Image Recovery from Compressed Measurements

Hyperspectral Target Detection via Adaptive Information—Theoretic Metric Learning with Local Constraints

Hyperspectral Anomaly Detection via Background Estimation and Adaptive Weighted Sparse Representation

Contact Info

Product

Resources

About