Supervised learning for labelling human body with attached props
| Data(s) |
01/06/2015
|
|---|---|
| Resumo |
In this research, a novel method for generating training data of human postures with attached objects is proposed. The results has shown a significant increase in body-part classification accuracy for subjects with props from 60% to 94% using the generated image set |
| Identificador | |
| Idioma(s) |
eng |
| Publicador |
Deakin Univeristy, Centre for Integelligent Systems Research, Centre for Integelligent Systems Research |
| Relação |
http://dro.deakin.edu.au/eserv/DU:30079441/haggag-agreement-2015.pdf http://dro.deakin.edu.au/eserv/DU:30079441/haggag-supervisedlearning-2015A.pdf |
| Direitos |
The Author. All Rights Reserved |
| Palavras-Chave | #training data of human postures #body-part classification accuracy #human body tracking and labelling #attached objects |
| Tipo |
Thesis |
