Show simple item record

dc.contributor.advisorPradalier, Cedric
dc.contributor.advisorAlRegib, Ghassan
dc.contributor.authorRichard, Antoine
dc.date.accessioned2018-01-22T21:14:02Z
dc.date.available2018-01-22T21:14:02Z
dc.date.created2017-12
dc.date.submittedDecember 2017
dc.identifier.urihttp://hdl.handle.net/1853/59291
dc.description.abstractThe overall objective of our project is to be able to classify the evolution of land usage since the advent of aerial imagery. In practice our aim is to bring automatic habitat classification to the level achieved by a human expert performing a fine-scale classification of habitat at resolutions covering from hedges and lake to fields, pastures or forest. Relying on the recent progresses in machine learning algorithm and in particular convolutional neural networks trained using deep learning (e.g. SegNet, DeepLab), our approach trains a machine to segment an overhead imagery into a dozen of expert-specified land use classes.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectDeep Learning
dc.subjectNeural Networks
dc.subjectAuto-encoders
dc.subjecthabitat segmentation
dc.subjectComputer Vision
dc.subjectMachine Learning
dc.subjectland use detection
dc.titleAutomated analysis of overhead imagery for habitat segmentation
dc.typeThesis
dc.description.degreeM.S.
dc.contributor.departmentElectrical and Computer Engineering
thesis.degree.levelMasters
dc.contributor.committeeMemberVoss, Paul
dc.contributor.committeeMemberAnderson, David
dc.contributor.committeeMemberOwen, Henry
dc.date.updated2018-01-22T21:14:02Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record