Digital video moving object segmentation using tensor voting: A non-causal, accurate approach

Simple item page
dc.contributor.advisorNicolls, Freden_ZA
dc.contributor.authorGuest, Ianen_ZA
dc.date.accessioned2014-07-31T10:57:04Z
dc.date.available2014-07-31T10:57:04Z
dc.date.issued2009en_ZA
dc.description.abstractMotion based video segmentation is important in many video processing applications such as MPEG4. This thesis presents an exhaustive, non-causal method to estimate boundaries between moving objects in a video clip. It make use of tensor voting principles. The tensor voting is adapted to allow image structure to manifest in the tangential plane of the saliency map. The technique allows direct estimation of motion vectors from second-order tensor analysis. The tensors make maximal and direct use of the available information by encoding it into the dimensionality of the tensor. The tensor voting methodology introduces a non-symmetrical voting kernel to allow a measure of voting skewness to be inferred. Skewness is found in the third-order tensor in the direction of the tangential first eigenvector. This new concept is introduced as the Tensor Skewness Map or TS map. The TS map gives further information about whether an object is occluding or disoccluding another object. The information can be used to infer the layering order of the moving objects in the video clip. Matched filtering and detection are applied to reduce the TS map into occluding and disoccluding detections. The technique is computationally exhaustive, but may find use in off-line video object segmentation processes. The use of commercial-off-the-shelf Graphic Processor Units is demonstrated to scale well to the tensor voting framework, providing the computational speed improvement required to make the framework realisable on a larger scale and to handle tensor dimensionalities higher than before.en_ZA
dc.identifier.apacitationGuest, I. (2009). <i>Digital video moving object segmentation using tensor voting: A non-causal, accurate approach</i>. (Thesis). University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/5209en_ZA
dc.identifier.chicagocitationGuest, Ian. <i>"Digital video moving object segmentation using tensor voting: A non-causal, accurate approach."</i> Thesis., University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2009. http://hdl.handle.net/11427/5209en_ZA
dc.identifier.citationGuest, I. 2009. Digital video moving object segmentation using tensor voting: A non-causal, accurate approach. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Guest, Ian AB - Motion based video segmentation is important in many video processing applications such as MPEG4. This thesis presents an exhaustive, non-causal method to estimate boundaries between moving objects in a video clip. It make use of tensor voting principles. The tensor voting is adapted to allow image structure to manifest in the tangential plane of the saliency map. The technique allows direct estimation of motion vectors from second-order tensor analysis. The tensors make maximal and direct use of the available information by encoding it into the dimensionality of the tensor. The tensor voting methodology introduces a non-symmetrical voting kernel to allow a measure of voting skewness to be inferred. Skewness is found in the third-order tensor in the direction of the tangential first eigenvector. This new concept is introduced as the Tensor Skewness Map or TS map. The TS map gives further information about whether an object is occluding or disoccluding another object. The information can be used to infer the layering order of the moving objects in the video clip. Matched filtering and detection are applied to reduce the TS map into occluding and disoccluding detections. The technique is computationally exhaustive, but may find use in off-line video object segmentation processes. The use of commercial-off-the-shelf Graphic Processor Units is demonstrated to scale well to the tensor voting framework, providing the computational speed improvement required to make the framework realisable on a larger scale and to handle tensor dimensionalities higher than before. DA - 2009 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2009 T1 - Digital video moving object segmentation using tensor voting: A non-causal, accurate approach TI - Digital video moving object segmentation using tensor voting: A non-causal, accurate approach UR - http://hdl.handle.net/11427/5209 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/5209
dc.identifier.vancouvercitationGuest I. Digital video moving object segmentation using tensor voting: A non-causal, accurate approach. [Thesis]. University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2009 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/5209en_ZA
dc.language.isoeng
dc.publisher.departmentDepartment of Electrical Engineeringen_ZA
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherElectrical Engineeringen_ZA
dc.titleDigital video moving object segmentation using tensor voting: A non-causal, accurate approachen_ZA
dc.typeDoctoral Thesis
dc.type.qualificationlevelDoctoral
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_ebe_2009_guest_ian.pdf
Size:
2.81 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Other Theses