Detection of ephemeral changes in sequences of images

Theiler, James; Adler‐Golden, Steven M.

doi:10.1109/aipr.2008.4906469

Cited by 8 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…41 There has also been research into using parametric distributions, 42 kernelized distributions, 43 spatio-spectral distributions, 44 and sequences of images. 45,46…”

Section: Theorymentioning

confidence: 99%

Multi-sensor anomalous change detection in remote sensing imagery

Ziemann

Ren

Theiler

2021

J. Appl. Rem. Sens.

Self Cite

View full text Add to dashboard Cite

Combining multiple satellite remote sensing sources provides a far richer, more frequent view of the earth than that of any single source; the challenge is in distilling these petabytes of heterogeneous sensor imagery into meaningful characterizations of the imaged areas. Meeting this challenge requires effective algorithms for combining multi-modal imagery over time to identify subtle but real changes among the intrinsic data variation. Here, we implement a jointdistribution framework for multi-sensor anomalous change detection (MSACD) that can effectively account for these differences in modality, and does not require any signal resampling of the pixel measurements. This flexibility enables the use of satellite imagery from different sensor platforms and modalities. We use multi-year construction of the SoFi Stadium in California as our testbed, and exploit synthetic aperture radar imagery from Sentinel-1 and multispectral imagery from both Sentinel-2 and Landsat 8. We show results for MSACD using real imagery with implanted, measurable changes, as well as real imagery with real, observable changes, including scaling our analysis over multiple years. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…41 There has also been research into using parametric distributions, 42 kernelized distributions, 43 spatio-spectral distributions, 44 and sequences of images. 45,46…”

Section: Theorymentioning

confidence: 99%

Multi-sensor anomalous change detection in remote sensing imagery

Ziemann

Ren

Theiler

2021

J. Appl. Rem. Sens.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The EC decision functions are point-wise nonlinear and still rely on second-order feature relations. Recent advances in ACD have considered methods robust to pixel misregistration [58] and sequences of several images in RX and chronocrome settings [55].…”

Section: Arxiv:201204920v1 [Cscv] 9 Dec 2020mentioning

confidence: 99%

Kernel Anomalous Change Detection for Remote Sensing Imagery

Padrón-Hidalgo

Laparra

Longbotham

et al. 2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Anomalous change detection is an important problem in remote sensing image processing. Detecting not only pervasive but anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors based on covariance operators. In particular, this paper focuses on algorithms that utilize Gaussian and elliptically contoured distributions, and extend them to their nonlinear counterparts based on the theory of reproducing kernels in Hilbert spaces. The presented methods generalize their linear counterparts, based on the assumption of either Gaussian or elliptically-contoured distribution. We illustrate the performance of the introduced kernel methods in both pervasive and anomalous change detection problems involving both real and simulated changes in multi and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, Quickbird). A wide range of situations are studied, involving droughts, wildfires, and urbanization in real examples. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false alarm rates. Results also reveal that the ellipticallycontoured assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios.

show abstract

“…One method uses the matched filter technique [2] with an appropriately defined target "spectrum". Another uses a simple modification of the RX anomaly detection method [3], which has previously used for fusion [4,5]. Both methods are reviewed here.…”

Section: Introductionmentioning

confidence: 99%

Automation of rare target detection via adaptive fusion

Adler‐Golden

Sundberg

2011

2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)

View full text Add to dashboard Cite

Fusing the outputs of multiple algorithms has been found to provide more consistent detection of rare targets in hyperspectral imagery. An analogous process that fuses different outputs from the same algorithm with different input parameter values also shows promise for eliminating the need for supervised parameter tuning. Together these strategies provide significant improvement in the consistency and automation of hyperspectral target detection. Results are presented for nine test cases involving both visible/near-infrared/shortwave-infrared and long-wavelength infrared hyperspectral imagery.

show abstract

Detection of ephemeral changes in sequences of images

Cited by 8 publications

References 12 publications

Multi-sensor anomalous change detection in remote sensing imagery

Multi-sensor anomalous change detection in remote sensing imagery

Kernel Anomalous Change Detection for Remote Sensing Imagery

Automation of rare target detection via adaptive fusion

Contact Info

Product

Resources

About