Paper Info
Title
Detection of small changes in complex urban and industrial scenes using imaging spectroscopy
Abstract
Hyperspectral change detection has been proved to be a promising technique for detecting indiscernible targets in different background. However, in the case of dense industrial and urban areas the complexity of the terrain and the multi-temporal images, which include positional deviation, radiant and atmospheric variation, shadows and spatial structure alteration, severely affects the automation of the change detection. This paper develops and enlarges four clustering based methods to detect man-made changes in VNIR and TIR hyperspectral scenes. The first applied method is Covariance-Equalisation (CE) multivariate statistical techniques, which detects differences between linear combinations of the spectral bands from the two acquisitions. The other three methods perform clustering of a reference image and then detect changes in a target image using a class-conditional distance detector: (a) class-conditional CE (QCE), (b) bi-temporal QCE and (c) Wavelength Dependent Segmentation (WDS). For the detection of small changes in industrial and urban areas, data from two flight campaigns were used: AHS-160 over the port of Antwerp and over the city of Kalmthout (Belgium). It was found that the use of a spatially adaptive detector greatly increases change-detection performance for both target detection and false alarm reduction. Moreover, WDS clustering based methods demonstrated a substantial improvement in change detection when applied on combined-wavelengths (as MWIR and LWIR or VNIR and TIR) hyperspectral data sets with respect to a single-wavelength data set.
Year
DOI
Venue
2010
10.1109/IGARSS.2010.5653711
Geoscience and Remote Sensing Symposium
Keywords
Field
DocType
covariance analysis,geophysical image processing,image segmentation,object detection,pattern clustering,spectroscopy,target tracking,TIR hyperspectral scene,VNIR hyperspectral scene,WDS clustering,atmospheric variation,bitemporal QCE,change-detection performance,class-conditional CE,class-conditional distance detector,complex urban scene,covariance-equalisation multivariate statistical technique,false alarm reduction,hyperspectral change detection,imaging spectroscopy,industrial scene,man-made change detection,multitemporal image,positional deviation,radiant variation,shadow,spatial structure alteration,spatially adaptive detector,spectral band,target detection,terrain complexity,wavelength dependent segmentation
Computer vision,Object detection,Data set,Change detection,Computer science,Remote sensing,Image segmentation,Hyperspectral imaging,Artificial intelligence,Covariance matrix,Cluster analysis,Imaging spectroscopy
Conference
ISSN
ISBN
Citations 
2153-6996 E-ISBN : 978-1-4244-9564-1
978-1-4244-9564-1
0
PageRank 
References 
Authors
0.34
2
3
Name
Order
Citations
PageRank
Michal Shimoni15611.17
Roel Heremans2663.91
Christiaan Perneel3195.03