Skip navigation
Skip navigation

Multi-class Semantic Video Segmentation with Exemplar-Based Object Reasoning

Liu, Buyu; He, Xuming; Gould, Stephen

Description

We tackle the problem of semantic segmentation of dynamic scene in video sequences. We propose to incorporate foreground object information into pixel labeling by jointly reasoning semantic labels of super-voxels, object instance tracks and geometric relations between objects. We take an exemplar approach to object modeling by using a small set of object annotations and exploring the temporal consistency of object motion. After generating a set of moving object hypotheses, we design a CRF...[Show more]

dc.contributor.authorLiu, Buyu
dc.contributor.authorHe, Xuming
dc.contributor.authorGould, Stephen
dc.coverage.spatialHonolulu, USA
dc.date.accessioned2016-06-14T23:21:15Z
dc.date.createdJanuary 5-9 2015
dc.identifier.isbn9781479966820
dc.identifier.urihttp://hdl.handle.net/1885/103799
dc.description.abstractWe tackle the problem of semantic segmentation of dynamic scene in video sequences. We propose to incorporate foreground object information into pixel labeling by jointly reasoning semantic labels of super-voxels, object instance tracks and geometric relations between objects. We take an exemplar approach to object modeling by using a small set of object annotations and exploring the temporal consistency of object motion. After generating a set of moving object hypotheses, we design a CRF framework that jointly models the super voxel and object instances. The optimal semantic labeling is inferred by the MAP estimation of the model, which is solved by a single move-making based optimization procedure. We demonstrate the effectiveness of our method on three public datasets and show that our model can achieve superior or comparable results than the state of-the-art with less object-level supervision
dc.publisherIEEE
dc.relation.ispartofseries2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
dc.sourceProceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
dc.titleMulti-class Semantic Video Segmentation with Exemplar-Based Object Reasoning
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2015
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationu4334215xPUB1537
local.type.statusPublished Version
local.contributor.affiliationLiu, Buyu, College of Engineering and Computer Science, ANU
local.contributor.affiliationHe, Xuming, College of Engineering and Computer Science, ANU
local.contributor.affiliationGould, Stephen, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage1014
local.bibliographicCitation.lastpage1021
local.identifier.doi10.1109/WACV.2015.140
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2016-06-14T09:03:35Z
local.identifier.scopusID2-s2.0-84925438468
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Liu_Multi-class_Semantic_Video_2015.pdf823.36 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator