File Download
Supplementary

postgraduate thesis: Motion segmentation by adaptive mode seeking and clustering consensus

TitleMotion segmentation by adaptive mode seeking and clustering consensus
Authors
Advisors
Advisor(s):Wong, KKY
Issue Date2012
PublisherThe University of Hong Kong (Pokfulam, Hong Kong)
Abstract
The task of multi-body motion segmentation refers to segmenting feature trajectories in a sequence of images according to their 3D motion affinity without knowing the number of motions in advance. It is critical for understanding and reconstructing a dynamic scene. This problem essentially consists of two subproblems, segmenting features and detecting the number of motions. While the state-of-the-art LBF algorithm achieves segmentation accuracy as high as 96.5%, it is still disturbed by a phenomenon called over-locality. A novel mode seeking algorithm with an adaptive distance measure is proposed to avoid this problem, and improves the accuracy to 98.1%. The LBF algorithm is incapable of detecting the number of motions itself. A randomized version of the mode seeking algorithm is presented, which could detect the number as well as preserve satisfactory segmentation accuracy. To detect the number of motions, a kernel optimization method locates it via kernel alignment. However, it suffers from over-locality and over-detects the number of motions. An intersection measure and two mutual information measures are presented to solve this problem. Using these measures, the proposed clustering consensus framework recasts the motion number detection problem to a clustering consensus problem. It extends the kernel optimization method from two-clustering consensus to multiple-clustering consensus. A large number of experiments and comparisons have been done, and convincing results are obtained.
DegreeDoctor of Philosophy
SubjectComputer vision.
Computer algorithms.
Cluster analysis.
Dept/ProgramComputer Science

 

DC FieldValueLanguage
dc.contributor.advisorWong, KKY-
dc.contributor.authorPan, Guodong.-
dc.contributor.author潘国栋.-
dc.date.issued2012-
dc.description.abstractThe task of multi-body motion segmentation refers to segmenting feature trajectories in a sequence of images according to their 3D motion affinity without knowing the number of motions in advance. It is critical for understanding and reconstructing a dynamic scene. This problem essentially consists of two subproblems, segmenting features and detecting the number of motions. While the state-of-the-art LBF algorithm achieves segmentation accuracy as high as 96.5%, it is still disturbed by a phenomenon called over-locality. A novel mode seeking algorithm with an adaptive distance measure is proposed to avoid this problem, and improves the accuracy to 98.1%. The LBF algorithm is incapable of detecting the number of motions itself. A randomized version of the mode seeking algorithm is presented, which could detect the number as well as preserve satisfactory segmentation accuracy. To detect the number of motions, a kernel optimization method locates it via kernel alignment. However, it suffers from over-locality and over-detects the number of motions. An intersection measure and two mutual information measures are presented to solve this problem. Using these measures, the proposed clustering consensus framework recasts the motion number detection problem to a clustering consensus problem. It extends the kernel optimization method from two-clustering consensus to multiple-clustering consensus. A large number of experiments and comparisons have been done, and convincing results are obtained.-
dc.languageeng-
dc.publisherThe University of Hong Kong (Pokfulam, Hong Kong)-
dc.relation.ispartofHKU Theses Online (HKUTO)-
dc.rightsThe author retains all proprietary rights, (such as patent rights) and the right to use in future works.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.source.urihttp://hub.hku.hk/bib/B48199369-
dc.subject.lcshComputer vision.-
dc.subject.lcshComputer algorithms.-
dc.subject.lcshCluster analysis.-
dc.titleMotion segmentation by adaptive mode seeking and clustering consensus-
dc.typePG_Thesis-
dc.identifier.hkulb4819936-
dc.description.thesisnameDoctor of Philosophy-
dc.description.thesisleveldoctoral-
dc.description.thesisdisciplineComputer Science-
dc.description.naturepublished_or_final_version-
dc.date.hkucongregation2012-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats