Show simple item record Dee, Hannah Mary Cohn, Anthony G. Hogg, David C. 2012-03-13T12:14:18Z 2012-03-13T12:14:18Z 2012-03-13
dc.identifier.citation Dee , H M , Cohn , A G & Hogg , D C 2012 , ' Building semantic scene models from unconstrained video ' Computer Vision and Image Understanding , vol 116 , no. 3 , pp. 446-456 . DOI: 10.1016/j.cviu.2011.09.005 en
dc.identifier.issn 1077-3142
dc.identifier.other PURE: 175313
dc.identifier.other PURE UUID: 5ac23f65-3a6c-4d61-814f-5159a03f070e
dc.identifier.other dspace: 2160/7801
dc.identifier.other DSpace_20121128.csv: row: 4616
dc.identifier.other RAD: 10566
dc.identifier.other RAD_Outputs_All_ID_Import_20121105.csv: row: 3773
dc.identifier.other Scopus: 84856083003
dc.description.abstract This paper describes a method for building semantic scene models from video data using observed motion. We do this through unsupervised clustering of simple yet novel motion descriptors, which provide a quantized representation of gross motion within scene regions. Using these we can characterise the dominant patterns of motion, and then group spatial regions based upon both proximity and local motion similarity to define areas or regions with particular motion characteristics. We are able to process scenes in which objects are difficult to detect and track due to variable frame-rate, video quality or occlusion, and we are able to identify regions which differ by usage but which do not differ by appearance (such as frequently used paths across open space). We demonstrate our method on 50 videos from very different scene types: indoor scenarios with unpredictable unconstrained motion, junction scenes, road and path scenes, and open squares or plazas. We show that these scenes can be clustered using our representation, and that the incorporation of learned spatial relations into the representation enables us to cluster more effectively. This method enables us to make meaningful statements about video scenes as a whole (such as “this video is like that video”) and about regions within these scenes (such as “this part of this scene is similar to that part of that scene”). en
dc.format.extent 11 en
dc.language.iso eng
dc.relation.ispartof Computer Vision and Image Understanding en
dc.rights en
dc.subject Scene understanding en
dc.subject Machine learning en
dc.subject Human behaviour en
dc.title Building semantic scene models from unconstrained video en
dc.type /dk/atira/pure/researchoutput/researchoutputtypes/contributiontojournal/article en
dc.contributor.institution Vision, Graphics and Visualisation Group en
dc.contributor.institution Department of Computer Science en
dc.description.status Peer reviewed en

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Cadair

Advanced Search