BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Eastern
BEGIN:DAYLIGHT
DTSTART:20180311T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20181104T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20180830T191643Z
UID:9A1A6A2D-1D38-43A1-8919-58F5BC180E70
DTSTART;TZID=US/Eastern:20180829T153000
DTEND;TZID=US/Eastern:20180829T163000
DESCRIPTION:In this lecture we will discuss how to combine the output of fu
 zzy clustering algorithms to detect the changes in remote sensing images. 
 In this regard we select two classical fuzzy clustering algorithms\, namel
 y fuzzy c-means (FCM) and Gustafson Kessel clustering (GKC). For clusterin
 g purpose various image features are extracted using the neighborhood info
 rmation of pixels from the difference image. To assign a pixel-pattern to 
 either of two groups (for changed and unchanged regions) maximum of the tw
 o membership-values (given by FCM and by GKC for the same pattern for same
  cluster) is considered. It has been observed experimentally that the chan
 ges are detected more efficiently using the proposed ensemble-based proced
 ure. To show the effectiveness of the proposed technique\, experiments are
  conducted on three multispectral and multitemporal remote sensing images.
  Results are compared with those of existing stand-alone fuzzy clustering 
 based algorithms and found to be superior.\n\nSpeaker(s): Ashish Ghosh\, \
 n\nRoom: 1125\, Bldg: Building 76\, 54 Lomb Memorial Drive\, Rochester\, N
 ew York\, United States\, 14623
LOCATION:Room: 1125\, Bldg: Building 76\, 54 Lomb Memorial Drive\, Rocheste
 r\, New York\, United States\, 14623
ORGANIZER:emmett@cis.rit.edu
SEQUENCE:5
SUMMARY:Combination of Fuzzy Clustering Algorithms for Change Detection in 
 Remote Sensing Images
URL;VALUE=URI:https://events.vtools.ieee.org/m/175997
X-ALT-DESC:Description: <br /><p>In this lecture we will discuss how to com
 bine the output of fuzzy clustering algorithms to detect the changes in re
 mote sensing images. In this regard we select two classical fuzzy clusteri
 ng algorithms\, namely fuzzy c-means (FCM) and Gustafson Kessel clustering
  (GKC). For clustering purpose various image features are extracted using 
 the neighborhood information of pixels from the difference image. To assig
 n a pixel-pattern to either of two groups (for changed and unchanged regio
 ns) maximum of the two membership-values (given by FCM and by GKC for the 
 same pattern for same cluster) is considered. It has been observed experim
 entally that the changes are detected more efficiently using the proposed 
 ensemble-based procedure. To show the effectiveness of the proposed techni
 que\, experiments are conducted on three multispectral and multitemporal r
 emote sensing images. Results are compared with those of existing stand-al
 one fuzzy clustering based&nbsp\; algorithms and found to be superior.</p>
END:VEVENT
END:VCALENDAR