Appearance modeling under geometric context for object recognition in videos

Simple item page
dc.contributor.advisorChellappa, Ramaen_US
dc.contributor.authorLi, Jianen_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2006-09-12T05:54:02Z
dc.date.available2006-09-12T05:54:02Z
dc.date.issued2006-08-03en_US
dc.description.abstractObject recognition is a very important high-level task in surveillance applications. This dissertation focuses on building appearance models for object recognition and exploring the relationship between shape and appearance for two key types of objects, human and vehicle. The dissertation proposes a generic framework that models the appearance while incorporating certain geometric prior information, or the so-called geometric context. Then under this framework, special methods are developed for recognizing humans and vehicles based on their appearance and shape attributes in surveillance videos. The first part of the dissertation presents a unified framework based on a general definition of geometric transform (GeT) which is applied to modeling object appearances under geometric context. The GeT models the appearance by applying designed functionals over certain geometric sets. GeT unifies Radon transform, trace transform, image warping etc. Moreover, five novel types of GeTs are introduced and applied to fingerprinting the appearance inside a contour. They include GeT based on level sets, GeT based on shape matching, GeT based on feature curves, GeT invariant to occlusion, and a multi-resolution GeT (MRGeT) that combines both shape and appearance information. The second part focuses on how to use the GeT to build appearance models for objects like walking humans, which have articulated motion of body parts. This part also illustrates the application of GeT for object recognition, image segmentation, video retrieval, and image synthesis. The proposed approach produces promising results when applied to automatic body part segmentation and fingerprinting the appearance of a human and body parts despite the presence of non-rigid deformations and articulated motion. It is very important to understand the 3D structure of vehicles in order to recognize them. To reconstruct the 3D model of a vehicle, the third part presents a factorization method for structure from planar motion. Experimental results show that the algorithm is accurate and fairly robust to noise and inaccurate calibration. Differences and the dual relationship between planar motion and planar object are also clarified in this part. Based on our method, a fully automated vehicle reconstruction system has been designed.en_US
dc.format.extent4831402 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/3846
dc.language.isoen_US
dc.subject.pqcontrolledEngineering, Electronics and Electricalen_US
dc.subject.pquncontrolledgeometric transformen_US
dc.subject.pquncontrolledappearance modelingen_US
dc.subject.pquncontrolledobject recognitionen_US
dc.subject.pquncontrolledstructure from motionen_US
dc.subject.pquncontrolledplanar motionen_US
dc.subject.pquncontrolledhuman identificationen_US
dc.titleAppearance modeling under geometric context for object recognition in videosen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
umi-umd-3692.pdf
Size:
4.61 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Electrical & Computer Engineering Theses and Dissertations