Title :
A new method for change analysis of multi-temporal hyperspectral images
Author_Institution :
Dept. of Electr. & Comput. Eng., Mississippi State Univ., Starkville, MS, USA
Abstract :
In this paper, we propose a new method based on tensor factorization (TF) for hyperspectral change detection. The multilinear algebra is used to consider the whole data of multi-temporal images. The tensor-based representation and analysis has the advantage of keeping the spatial, spectral, and temporal structures in the original images. The preliminary result shows that this new method is capable of finding the foreground changes of interest in the presence of diurnal and seasonal variations.
Keywords :
hyperspectral imaging; image representation; matrix decomposition; object detection; tensors; TF; change analysis; diurnal variation; hyperspectral change detection; multi-temporal hyperspectral images; multilinear algebra; seasonal variation; spatial structure; spectral structure; temporal structure; tensor factorization; tensor-based analysis; tensor-based representation; Abstracts; Indexes; Matrix decomposition; Monitoring; Object recognition; Radiometry; Change detection; higher order orthogonal iteration (HOOI) algorithm; hyperspectral imagery; matrix factorization (MF); principal component analysis (PCA); tensor factorization (TF);
Conference_Titel :
Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2012 4th Workshop on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4799-3405-8
DOI :
10.1109/WHISPERS.2012.6874223