Minimum Delay Moving Object Detection

Handle URI:
http://hdl.handle.net/10754/623619
Title:
Minimum Delay Moving Object Detection
Authors:
Lao, Dong ( 0000-0001-9308-7085 )
Abstract:
This thesis presents a general framework and method for detection of an object in a video based on apparent motion. The object moves, at some unknown time, differently than the “background” motion, which can be induced from camera motion. The goal of proposed method is to detect and segment the object as soon it moves in an online manner. Since motion estimation can be unreliable between frames, more than two frames are needed to reliably detect the object. Observing more frames before declaring a detection may lead to a more accurate detection and segmentation, since more motion may be observed leading to a stronger motion cue. However, this leads to greater delay. The proposed method is designed to detect the object(s) with minimum delay, i.e., frames after the object moves, constraining the false alarms, defined as declarations of detection before the object moves or incorrect or inaccurate segmentation at the detection time. Experiments on a new extensive dataset for moving object detection show that our method achieves less delay for all false alarm constraints than existing state-of-the-art.
Advisors:
Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Committee Member:
Genton, Marc G. ( 0000-0001-6467-2998 ) ; Shamma, Jeff S. ( 0000-0001-5638-9551 )
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Program:
Applied Mathematics and Computational Science
Issue Date:
14-May-2017
Type:
Thesis
Appears in Collections:
Theses

Full metadata record

DC FieldValue Language
dc.contributor.advisorSundaramoorthi, Ganeshen
dc.contributor.authorLao, Dongen
dc.date.accessioned2017-05-16T05:37:32Z-
dc.date.available2017-05-16T05:37:32Z-
dc.date.issued2017-05-14-
dc.identifier.urihttp://hdl.handle.net/10754/623619-
dc.description.abstractThis thesis presents a general framework and method for detection of an object in a video based on apparent motion. The object moves, at some unknown time, differently than the “background” motion, which can be induced from camera motion. The goal of proposed method is to detect and segment the object as soon it moves in an online manner. Since motion estimation can be unreliable between frames, more than two frames are needed to reliably detect the object. Observing more frames before declaring a detection may lead to a more accurate detection and segmentation, since more motion may be observed leading to a stronger motion cue. However, this leads to greater delay. The proposed method is designed to detect the object(s) with minimum delay, i.e., frames after the object moves, constraining the false alarms, defined as declarations of detection before the object moves or incorrect or inaccurate segmentation at the detection time. Experiments on a new extensive dataset for moving object detection show that our method achieves less delay for all false alarm constraints than existing state-of-the-art.en
dc.language.isoenen
dc.subjectobject detectionen
dc.subjectmotion segmentationen
dc.subjectoptimal delayen
dc.titleMinimum Delay Moving Object Detectionen
dc.typeThesisen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
thesis.degree.grantorKing Abdullah University of Science and Technologyen_GB
dc.contributor.committeememberGenton, Marc G.en
dc.contributor.committeememberShamma, Jeff S.en
thesis.degree.disciplineApplied Mathematics and Computational Scienceen
thesis.degree.nameMaster of Scienceen
dc.person.id142802en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.