A Neural architecture for recognising human actions in video sequences

Simple item page
dc.contributor.advisorDu Preez, Johanen_ZA
dc.contributor.authorMalan, Christianen_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Electrical and Electronic Engineering.en_ZA
dc.date.accessioned2022-03-02T10:22:38Z
dc.date.accessioned2022-04-29T09:41:15Z
dc.date.available2022-03-02T10:22:38Z
dc.date.available2022-04-29T09:41:15Z
dc.date.issued2022-04
dc.descriptionThesis (MEng)--Stellenbosch University, 2022.en_ZA
dc.description.abstractENGLISH ABSTRACT: The goal of an action recognition model (as applied to a video) is to extract distinct features that accurately characterise the action present and then from that determine the dominant action in the video. Since such actions occur in the spatio-temporal domain, recognising it relies on both spatial and temporal features. In this thesis we designed and built such an action recognition model by making use of a deep neural network system that combines various subsystems, each focussing on complemen tary aspects of the problem. A particular focus is on the automatic extraction of discriminatory spatio-temporal features. In combination the final system is shown to accurately distinguish between a limited range of actions.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Die doel van ’n aksieherkenningsmodel (soos toegepas op ’n video) is om eerstens duidelike kenmerke te onttrek wat die aksie akkuraat beskryf, en dan daaruit die dominante aksie teenwoordig in die video te bepaal. Aangesien sulke aksies in beide tyd en ruimte plaasvind, moet ’n herkenner beide van hierdie domeine in ag neem. In hierdie tesis het ons ’n diep neuralenetwerk stelsel vir hierdie doel ontwikkel. Dit maak gebruik van verskeie substelsels wat elk fokus op komplementêre aspekte van die probleem. ’n Besondere fokus is op die outomatiese onttrekking van diskriminerende tydruimtelike kenmerke. In kombinasie is die finale stelsel in staat om ’n beperkte reeks aksies akkuraat te onderskei.af_ZA
dc.description.versionMastersen_ZA
dc.format.extent135 pagesen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/124921
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectUCTDen_ZA
dc.subjectNeural network computersen_ZA
dc.subjectArtificial intelligenceen_ZA
dc.subjectAction recognition modelen_ZA
dc.titleA Neural architecture for recognising human actions in video sequencesen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
malan_neural_2022.pdf
Size:
10.96 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Electrical and Electronic Engineering)