BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Applied Mathematical Problems of Visual Objects Localization under
  Resource Constraints (Прикладнi математичнi задачi
  вiзуальної локалiзацiї об’єктiв за умови
  обмежених ресурсiв) Атестація у зв'язку 
 із підготовленою дисертацією
DTSTART;VALUE=DATE-TIME:20260612T090000Z
DTEND;VALUE=DATE-TIME:20260612T110000Z
DTSTAMP;VALUE=DATE-TIME:20260622T151600Z
UID:indico-event-2156@events.imath.kiev.ua
DESCRIPTION:Speakers: Олег Самойленко (Інститут ма
 тематики НАН України)\n\nThe thesis addresses an applied
  mathematics problem at the intersec- tion of computer vision\, image proc
 essing\, and robotics: the visual local- ization of a mobile platform in e
 nvironments where the Global Positioning System (GPS) is degraded or unava
 ilable\, under the explicit resource con- straints of onboard embedded har
 dware. Two research lines shape the practical setting: the extraction and 
 geometric verification of visual cor- respondences on the vision side\, an
 d the recursive fusion of noisy sensor measurements on the state-estimatio
 n side\; the two have evolved largely independently. The thesis treats the
 m as a single problem of recursive state estimation for a planar mobile pl
 atform\, into which the quality of the visual matching enters as an adapta
 tion signal that scales the measure- ment covariance. Feature detection\, 
 matching\, and state estimation are required to run on CPU-only platforms\
 , so the accuracy of every method is quantified against its computational 
 cost rather than in isolation.\n\nThe objective of the thesis is to develo
 p a sensor-fusion framework for the localization of a planar mobile robot 
 that combines wheel odometry and GPS\, to extend it with a visual position
  observation derived from satellite image matching whose measurement covar
 iance is scaled by the matching- quality signal of the geometric-verificat
 ion stage\, and to support this with a comparative study of classical and 
 learned local feature descriptors under explicit resource constraints.\n\n
 Topic: Семінар відділу математичних пробле
 м механіки та теорії керування\nTime: Jun 12\, 2
 026 12:00 Kyiv\n\nJoin Zoom Meeting\nMeeting ID: 895 3163 1507\nPasscode: 
 423655\n\nhttps://events.imath.kiev.ua/event/2156/
URL:https://events.imath.kiev.ua/event/2156/
END:VEVENT
END:VCALENDAR
