University of Twente Student Theses

Login

An Approach at Social Relation Recognition in Egocentric Videos using Pose Estimation

Meijer, M.P. (2022) An Approach at Social Relation Recognition in Egocentric Videos using Pose Estimation.

[img] PDF
9MB
Abstract:In this paper, a literature review is conducted and a framework is analysed for the automatic recognition of social relations in egocentric videos. Background research is conducted, where different methods of recognising social relations in videos are compared. An approach is proposed where the supervised machine learning models Nearest Neighbors, Linear SVM, RBF SVM, Gaussian Process, Decision Tree, Random Forest, Neural Net, AdaBoost, Naive Bayes and QDA are applied to data generated by human pose estimation and tracking. Finally, various experiments are done to validate the proposed features and classifiers.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/91815
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page