Show simple item record

dc.contributor.advisorGhanem, Bernard
dc.contributor.authorLahoud, Jean
dc.date.accessioned2020-09-09T08:23:16Z
dc.date.available2020-09-09T08:23:16Z
dc.date.issued2020-09
dc.identifier.doi10.25781/KAUST-8L876
dc.identifier.urihttp://hdl.handle.net/10754/665033
dc.description.abstractOne of the main goals in computer vision is to achieve a human-like understanding of images. Nevertheless, image understanding has been mainly studied in the 2D image frame, so more information is needed to relate them to the 3D world. With the emergence of 3D sensors (e.g. the Microsoft Kinect), which provide depth along with color information, the task of propagating 2D knowledge into 3D becomes more attainable and enables interaction between a machine (e.g. robot) and its environment. This dissertation focuses on three aspects of indoor 3D scene understanding: (1) 2D-driven 3D object detection for single frame scenes with inherent 2D information, (2) 3D object instance segmentation for 3D reconstructed scenes, and (3) using room and floor orientation for automatic labeling of indoor scenes that could be used for self-supervised object segmentation. These methods allow capturing of physical extents of 3D objects, such as their sizes and actual locations within a scene.
dc.language.isoen
dc.subjectDepth sensors
dc.subject3D Understanding
dc.subject3D instance segmentation
dc.subject3D object detection
dc.subjectself-supervised pertaining
dc.subjectobject recognition
dc.titleIndoor 3D Scene Understanding Using Depth Sensors
dc.typeDissertation
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
thesis.degree.grantorKing Abdullah University of Science and Technology
dc.contributor.committeememberHeidrich, Wolfgang
dc.contributor.committeememberWonka, Peter
dc.contributor.committeememberCremers, Daniel
thesis.degree.disciplineElectrical Engineering
thesis.degree.nameDoctor of Philosophy
refterms.dateFOA2020-09-09T08:23:17Z
kaust.request.doiyes


Files in this item

Thumbnail
Name:
JeanLahoudThesis.pdf
Size:
22.25Mb
Format:
PDF
Description:
Final Thesis

This item appears in the following Collection(s)

Show simple item record