3D Object Representations for Recognition.
dc.contributor.author | Xiang, Yu | |
dc.date.accessioned | 2016-06-10T19:32:34Z | |
dc.date.available | NO_RESTRICTION | |
dc.date.available | 2016-06-10T19:32:34Z | |
dc.date.issued | 2016 | |
dc.date.submitted | ||
dc.identifier.uri | https://hdl.handle.net/2027.42/120836 | |
dc.description.abstract | Object recognition from images is a longstanding and challenging problem in computer vision. The main challenge is that the appearance of objects in images is affected by a number of factors, such as illumination, scale, camera viewpoint, intra-class variability, occlusion, truncation, and so on. How to handle all these factors in object recognition is still an open problem. In this dissertation, I present my efforts in building 3D object representations for object recognition. Compared to 2D appearance based object representations, 3D object representations can capture the 3D nature of objects and better handle viewpoint variation, occlusion and truncation in object recognition. I introduce three new 3D object representations: the 3D aspect part representation, the 3D aspectlet representation and the 3D voxel pattern representation. These representations are built to handle different challenging factors in object recognition. The 3D aspect part representation is able to capture the appearance change of object categories due to viewpoint transformation. The 3D aspectlet representation and the 3D voxel pattern representation are designed to handle occlusions between objects in addition to viewpoint change. Based on these representations, we propose new object recognition methods and conduct experiments on benchmark datasets to verify the advantages of our methods. Furthermore, we introduce, PASCAL3D+, a new large scale dataset for 3D object recognition by aligning objects in images with 3D CAD models. We also propose two novel methods to tackle object co-detection and multiview object tracking using our 3D aspect part representation, and a novel Convolutional Neural Network-based approach for object detection using our 3D voxel pattern representation. In order to track multiple objects in videos, we introduce a new online multi-object tracking framework based on Markov Decision Processes. Lastly, I conclude the dissertation and discuss future steps for 3D object recognition. | |
dc.language.iso | en_US | |
dc.subject | Computer Vision | |
dc.subject | Object Recognition | |
dc.subject | Object Representation | |
dc.subject | Object Tracking | |
dc.subject | Object Pose Estimation | |
dc.title | 3D Object Representations for Recognition. | |
dc.type | Thesis | en_US |
dc.description.thesisdegreename | PhD | |
dc.description.thesisdegreediscipline | Electrical Engineering: Systems | |
dc.description.thesisdegreegrantor | University of Michigan, Horace H. Rackham School of Graduate Studies | |
dc.contributor.committeemember | Hero(iii), Alfred O | |
dc.contributor.committeemember | Savarese, Silvio | |
dc.contributor.committeemember | Deng, Jia | |
dc.contributor.committeemember | Corso, Jason | |
dc.subject.hlbsecondlevel | Electrical Engineering | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/120836/1/yuxiang_1.pdf | |
dc.identifier.orcid | 0000-0001-9431-5131 | |
dc.identifier.name-orcid | Xiang, Yu; 0000-0001-9431-5131 | en_US |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.