6533b821fe1ef96bd127b9bf
RESEARCH PRODUCT
Unsupervised change detection with kernels
Gustau Camps-vallsMichele VolpiDevis TuiaMikhail Kanevskisubject
Correctness010504 meteorology & atmospheric sciencesFeature extraction0211 other engineering and technologiesComposite kernels02 engineering and technologykernel parameters01 natural sciencesunsupervised change detectionElectrical and Electronic Engineeringkernel k-meansCluster analysis021101 geological & geomatics engineering0105 earth and related environmental sciencesMathematicsPixelbusiness.industryPattern recognitionGeotechnical Engineering and Engineering GeologyNonlinear systemKernel (image processing)Unsupervised learningArtificial intelligencebusinessChange detectiondescription
In this paper an unsupervised approach to change detection relying on kernels is introduced. Kernel based clustering is used to partition a selected subset of pixels representing both changed and unchanged areas. Once the optimal clustering is obtained the estimated representatives (centroids) of each group are used to assign the class membership to all others pixels composing the multitemporal scenes. Different approaches of considering the multitemporal information are considered with accent on the computation of the difference image directly in the feature spaces. For this purpose a difference kernel approach is successfully adopted. Finally an effective way to cope with the estimation of kernel parameters in a completely unsupervised way is proposed. Evidence of the correctness and superiority of the proposed solution is provided through the analysis of high and very high geometrical resolution (VHR) images.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2012-11-01 | IEEE Geoscience and Remote Sensing Letters |