Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/135474
DC FieldValue
dc.titlePATH PLANNING STRATEGIES FOR VISIBILITY ENHANCEMENT WITH UNMANNED AERIAL VEHICLES IN CLUTTERED ENVIRONMENTS
dc.contributor.authorVENGATESAN GOVINDARAJU
dc.date.accessioned2017-04-30T18:01:10Z
dc.date.available2017-04-30T18:01:10Z
dc.date.issued2017-01-19
dc.identifier.citationVENGATESAN GOVINDARAJU (2017-01-19). PATH PLANNING STRATEGIES FOR VISIBILITY ENHANCEMENT WITH UNMANNED AERIAL VEHICLES IN CLUTTERED ENVIRONMENTS. ScholarBank@NUS Repository.
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/135474
dc.description.abstractSmall-Unmanned Aerial Vehicles (SUAVs) provide significant advantages during search-and-rescue and civil security operations in urban and forested regions. However, their effective coverage area is reduced by occlusions in the field-of-view of the sensor. In this thesis, to obtain a quick and effective aerial surveillance, three path planning strategies are developed that enhances ground/target visibility. The first path planning approach improves the ground visibility in a forested environment. The gradual reduction in visibility along the line-of-sight in a forested region is modeled using the tree cover density. The waypoints are obtained using the Centroidal Voronoi Tessellation (CVT) method and the flight path through these waypoints is solved using an improved spiral-alternating algorithm. The second path planning approach maximizes the duration of visibility of a moving target in urban regions. A parallel Fast-marching method (FMM) is developed for fast 3D visibility computation. A Visibility-Based Fast-Marching field is developed for path planning to maximize visibility and minimize the path length. Another path planning strategy is proposed for searching and tracking moving targets in urban environments. The video feed obtained from the gimballed camera is used to detect and localize the target using photogrammetry. The target's position is tracked using particle filters and the k-medoids clustering method is used for path planning and determining the best view direction. Realistic simulations are performed and the results show the effectiveness of the proposed path planning methods in enhancing the visibility of targets in cluttered environments.
dc.language.isoen
dc.subjectPath planning, SUAV, Visibility, View Planning, Surveillance, Moving Target, Tracking, Gimballed Camera
dc.typeThesis
dc.contributor.departmentMECHANICAL ENGINEERING
dc.contributor.supervisorLENG SIEW BING, GERARD
dc.description.degreePh.D
dc.description.degreeconferredDOCTOR OF PHILOSOPHY
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Ph.D Theses (Open)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
GovindarajuVENGATESAN.pdf25.91 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

162
checked on Feb 2, 2023

Download(s)

215
checked on Feb 2, 2023

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.