Background-Annihilated Target-Constrained Interference-Minimized Filter (TCIMF) for Hyperspectral Target Detection

Chen, Jie; Chang, Chein‐I

doi:10.1109/tgrs.2022.3208519

Cited by 14 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input image size for all methods is M × N × L. In our method, b denotes the number of nodes in the latent space, while iter represents the number of layers in hCEM, which is on average 10. For CSCR, (w o ut, w i n) form the sliding double windows and are set to (11,3). The values of ncem and nlayer represent the number of CEM detectors used per layer and the number of layers in ECEM, respectively, with values of 6 and 10.…”

Section: Compared Methodsmentioning

confidence: 99%

“…Although many studies have been conducted on CEM and its variants, such as hCEM [9] and ECEM [10], their performance is limited due to the redundancy of spectral information and the limitations of imaging technology. In order to effectively tackle the intricate contextual issues in HSIs, Chen and Chang [11] adopted a comprehensive approach by integrating CEM and OSP techniques. As a result, they proposed a novel method called BKG-annihilated TCIMF method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ABLAL: Adaptive Background Latent Space Adversarial Learning Algorithm for Hyperspectral Target Detection

Sun,

Ma,

Zhang

2024

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

View full text Add to dashboard Cite

Hyperspectral images (HSIs) are challenging for hyperspectral object detection (HTD) due to their complex background information and the limited prior knowledge of the target. This paper proposes an adaptive background latent space adversarial learning algorithm for hyperspectral target detection (ABLAL). We begin by using a coarse screening method to select pseudo-background and pseudo-target sample sets, addressing the issues caused by insufficient prior target information and complicated background information, which result in low detection accuracy. Next, we utilize an Adversarial Autoencoder (AAE) based backbone network to extract the background latent spatial information of the HSI. It should be noted that we adaptively constrain the accuracy of the extracted information through the pseudo-target dataset, accounting for the impact of potential targets in the pseudo-background dataset. Furthermore, we fully utilize the information extracted by AAE and employ a strategy combining multiple output results of AAE. Specifically, we use the distance between the target latent space vector and the background latent space vector, and the HSI reconstruction difference to suppress the background. Finally, extensive experiments are conducted on real datasets to demonstrate the effectiveness of the proposed method.

show abstract

Section: Compared Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ABLAL: Adaptive Background Latent Space Adversarial Learning Algorithm for Hyperspectral Target Detection

Sun,

Ma,

Zhang

2024

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

View full text Add to dashboard Cite

show abstract

“…for all datasets. The dual-window sizes of the CSCR were set to (5,17), (9,13), (3,5), (13,15) and (15,19) for datasets I-V, respectively. The trade-off parameters of SLRMD were set to 0.01   and 1…”

Section: B Experimental Setup 1) Implementation Detailsmentioning

confidence: 99%

“…To solve the interference problem of complex background, Chang et al [18] integrated data segmentation, low-rank and sparse matrix decomposition (LRSMD) to extend OSP for performance enhancement. Subsequently, Chen et al [19] proposed a backgroundannihilated target-constrained interference-minimized filter. Specifically, data sphering, LRSMD, and component decomposition analysis are first used to annihilate background.…”

mentioning

confidence: 99%

Hyperspectral Target Detection via Global Spatial–Spectral Attention Network and Background Suppression

Wang,

Wang

et al. 2023

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

View full text Add to dashboard Cite

The accuracy of hyperspectral target detection (HTD) is often affected by the problems of spectral variation and complex background distribution. Inspired by the powerful representational ability of deep learning, we proposed a 3-D convolution-based global spatial-spectral attention network (GS 2 A-Net) to deal with spectral variation in hyperspectral images (HSIs). GS 2 A-Net uses 3-D convolution kernels of different sizes to capture local spatial and spectral features to achieve multi-scale information interaction. Different from the previous 2-D attention mechanisms, GS 2 A-Net simultaneously considers the information in the spatial and spectral dimensions, and creates a weight map consistent with the size of the original HSI. Furthermore, we proposed a new background suppression strategy based on spectral angle mapping (SAM) to achieve more accurate target detection, which can preserve the targets as much as possible when suppressing the background. The method was validated through experiments on five real-world HSI datasets. Compared with several classical and deep learning-based methods, the proposed method exhibits greater detection accuracy.  Index Terms-Hyperspectral target detection, spectral variation, global spatial-spectral attention network, background suppression. I. INTRODUCTION Hyperspectral sensors record hyperspectral images (HSIs) with hundreds of continuous and narrow bands, reaching a spectral resolution of around 10 nm. Due to its powerful representational ability, HSIs have been widely used in land cover classification [1], [2], target detection [3], [4], anomaly detection [5], [6], image unmixing [7], [8] and change detection [9]. Hyperspectral target detection (HTD) is one of the most challenging issues in these applications, due to the limited amount of known information about target spectra and the background. Indeed, HTD can be regarded as a problem of weakly supervised binary classification.

show abstract

“…With the advance of spectral imaging technologies and the subsequent improvement of spectral resolution, hyperspectral remote sensing data now provides extremely detailed information for earth observation [1][2][3][4]. Hyperspectral target detection [5][6][7][8][9][10] is one of the most important research directions in hyperspectral image processing. It utilizes the rich spectral information contained in hyperspectral images to effectively separate targets from background pixels.…”

Section: Introductionmentioning

confidence: 99%

CE-RX: A Collaborative Cloud-Edge Anomaly Detection Approach for Hyperspectral Images

Wang,

Cai,

Zhou

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Due to the constrained processing capabilities of real-time detection techniques in remote sensing applications, it is often difficult to obtain detection results with high accuracy in practice. To address this problem, we introduce a new real-time anomaly detection algorithm for hyperspectral images called cloud–edge RX (CE-RX). The algorithm combines the advantages of cloud and edge computing. During the data acquisition process, the edge performs real-time detection on the data just captured to obtain a coarse result and find the suspicious anomalies. At regular intervals, the suspicious anomalies are sent to the cloud for further detection with a highly accurate algorithm, then the cloud sends back the (high-accuracy) results to the edge for information updating. After receiving the results from the cloud, the edge updates the information of the detector in the real-time algorithm to improve the detection accuracy of the next acquired piece of data. Our experimental results demonstrate that the proposed cloud–edge collaborative algorithm can obtain more accurate results than existing real-time detection algorithms.

show abstract

Background-Annihilated Target-Constrained Interference-Minimized Filter (TCIMF) for Hyperspectral Target Detection

Abstract: County (UMBC)ScholarWorks@UMBC digital repository on the Maryland Shared Open Access (MD-SOAR) platform.

Cited by 14 publications

References 39 publications

ABLAL: Adaptive Background Latent Space Adversarial Learning Algorithm for Hyperspectral Target Detection

ABLAL: Adaptive Background Latent Space Adversarial Learning Algorithm for Hyperspectral Target Detection

Hyperspectral Target Detection via Global Spatial–Spectral Attention Network and Background Suppression

CE-RX: A Collaborative Cloud-Edge Anomaly Detection Approach for Hyperspectral Images

Contact Info

Product

Resources

About