A Tiny Diagnostic Dataset and Diverse Modules for Learning-Based Optical Flow Estimation

FieldValue
dc.contributor.authorXie, Shuang
dc.date.accessioned2019-09-18T18:48:22Z
dc.date.available2019-09-18T18:48:22Z
dc.date.issued2019-09-18
dc.identifier.urihttp://hdl.handle.net/10393/39634
dc.identifier.urihttp://dx.doi.org/10.20381/ruor-23877
dc.description.abstractRecent work has shown that flow estimation from a pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNN). However, the basic straightforward CNN methods estimate optical flow with motion and occlusion boundary blur. To tackle this problem, we propose a tiny diagnostic dataset called FlowClevr to quickly evaluate various modules that can use to enhance standard CNN architectures. Based on the experiments of the FlowClevr dataset, we find that a deformable module can improve model prediction accuracy by around 30% to 100% in most tasks and more significantly reduce boundary blur. Based on these results, we are able to design modifications to various existing network architectures improving their performance. Compared with the original model, the model with the deformable module clearly reduces boundary blur and achieves a large improvement on the MPI sintel dataset, an omni-directional stereo (ODS) and a novel omni-directional optical flow dataset.
dc.language.isoen
dc.publisherUniversité d'Ottawa / University of Ottawa
dc.subjectComputer Vision
dc.subjectOptical Flow
dc.subjectOmni-directional Image
dc.subjectPanoramic
dc.subjectCNN
dc.subjectDataset
dc.titleA Tiny Diagnostic Dataset and Diverse Modules for Learning-Based Optical Flow Estimation
dc.typeThesis
dc.contributor.supervisorLang, Jochen
thesis.degree.nameMSc
thesis.degree.levelMasters
thesis.degree.disciplineGénie / Engineering
uottawa.departmentScience informatique et génie électrique / Electrical Engineering and Computer Science
CollectionThèses, 2011 - // Theses, 2011 -

Files