Abstract
With the increase in the availability of multitemporal hyperspectral images (HSIs), HSIs change detection (CD) methods, including pixel-level and subpixel-level based methods, have attracted great attention in recent years. However, the widespread presence of mixed pixels in HSIs may make it difficult for pixel-level methods to detect subtle changes; meanwhile, the less utilization of spatial information may also lead to limitations in some subpixel-level methods. Therefore, a joint framework, which aims to combine the advantages of pixel-level in spatial utilization and subpixel-level in temporal and spectral exploration, is proposed to enhance the performance of HSIs CD. Two models, convolutional sparse analysis and temporal spectral unmixing, are introduced and presented to characterize different spatial structures and overcome the effects of spectral variability under this framework, respectively. In addition, a multiple CD-based on subpixel analysis is discussed as well. Experiments conducted on three bitemporal HSIs datasets indicate that the proposed framework is robust in capturing effective features and has achieved great detection accuracy.
Highlights
C OMPARED to multispectral images, hyperspectral images (HSIs) contain a higher number of spectral channels, with the ability to detect both subtle and multiple changes, which can be applied to many fields [1]–[3]
SPS is a spatial-spectral ensemble method that combines the first three principal components with the spatial features obtained by convolutional sparse analysis to form a feature cube, and uses Support Vector Machine (SVM) to detect the changes
This point can be obtained in the quantitative accuracy as well The reason may be that the sparse unmixing (SU) does not consider the effects of spectral variability in multitemporal images
Summary
C OMPARED to multispectral images, hyperspectral images (HSIs) contain a higher number of spectral channels, with the ability to detect both subtle and multiple changes, which can be applied to many fields [1]–[3]. The obtained spatial features of these methods usually tend to be blurry that obscure some important structural information of the input image This severely limits the effectiveness of joint analysis strategy on HSIs CD [19]. The SU approach begins with the ideas of sparse analysis and matrix factorization to detect subpixel-level information through spectral libraries In these methods, the spectral library is necessary, limiting the ranges of its application. Convolutional sparse analysis and temporal spectral unmixing, are proposed as the key techniques The former can achieve the effective spatial utilization at the pixel-level; the later enables the combination of spectral and temporal information. 1) A combination framework based on pixel-level and subpixel-level analysis is designed to address the shortcomings of existing CD methods in information exploitation.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
