Accession Number : ADA609694


Title :   Removing Parallax-Induced False Changes in Change Detection


Descriptive Note : Doctoral thesis


Corporate Author : AIR FORCE INSTITUTE OF TECHNOLOGY WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT


Personal Author(s) : Vongsy, Karmon M


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a609694.pdf


Report Date : 27 Mar 2014


Pagination or Media Count : 147


Abstract : Accurate change detection (CD) results in urban environments is of interest to a diverse set of applications including military surveillance, environmental monitoring, and urban development. This work presents a hyperspectral CD (HSCD) framework. The framework uncovers the need for HSCD methods that resolve false change caused by image parallax. A Generalized Likelihood Ratio Test (GLRT) statistic for HSCD is developed that accommodates unknown mis-registration between imagery described by a prior probability density function for the spatial mis-registration. The potential of the derived method to incorporate more complex signal proccessing functions is demonstrated by the incorporation of a parallax error mitigation component. Results demonstrate that parallax mitigation reduces false alarms.


Descriptors :   *CHANGE DETECTION , *HYPERSPECTRAL IMAGERY , ACCURACY , ENVIRONMENTS , ERRORS , FALSE ALARMS , IMAGES , MONITORING , PARALLAX COMPUTERS , PROBABILITY DENSITY FUNCTIONS , REMOVAL , SIGNALS , SPATIAL DISTRIBUTION , SURVEILLANCE , THESES , URBAN AREAS


Subject Categories : Optical Detection and Detectors


Distribution Statement : APPROVED FOR PUBLIC RELEASE