UNIGE document Doctoral Thesis
previous document  unige:95677  next document
add to browser collection
Title

Sparse multi-view 3D computer vision : application to embedded assistive technologies

Author
Directors
Hasler, David
Defense Thèse de doctorat : Univ. Genève, 2017 - Sc. 5090 - 2017/06/19
Abstract In the framework of 3D computer vision dedicated to assistive technologies, the research studies reported in this thesis have the objective to design new computer-vision-based approaches dedicated to embedded and real-time applications with limited resources. This thesis proposes novel strategies for rapid object detection and recognition under practical constraints. These limitations are for example the number of sensors and their resolution, algorithm complexity and mobile battery-life. We narrowed the research scope to specific objects and obstacles detection from off-the-shelf stereo and plenoptic cameras. The research work thus investigates two areas of computer vision from multi-view imaging, namely exploiting (i) sparse 3D keypoint clouds from stereo vision and (ii) light field imaging for low-complexity and efficient algorithms.
Keywords 3D computer visionObstacle detectionObject detectionPose estimationObject recognitionDepth estimationKeypoint detectionStereo visionLight fieldAssistive technologiesElderly rehabilitationWalkerEmbedded visionLow powerLow complexity
Identifiers
URN: urn:nbn:ch:unige-956778
Full text
Thesis (47.4 MB) - public document Free access
Structures
Research groups Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
Project Hasler Stiftung - Smart World Program
Citation
(ISO format)
CLOIX, Séverine. Sparse multi-view 3D computer vision : application to embedded assistive technologies. Université de Genève. Thèse, 2017. https://archive-ouverte.unige.ch/unige:95677

111 hits

21 downloads

Update

Deposited on : 2017-07-26

Export document
Format :
Citation style :