A Framework to Generate and Label Synthetic/Real Video Data to Feed Temporal Segment Networks
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/107802
Título: | A Framework to Generate and Label Synthetic/Real Video Data to Feed Temporal Segment Networks |
---|---|
Autor/es: | Allhoff, Daniel Finn |
Director de la investigación: | Garcia-Rodriguez, Jose | Castro-Vargas, John Alejandro |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Tecnología Informática y Computación |
Palabras clave: | Artificial intelligence | Software | Behaviour analysis |
Área/s de conocimiento: | Arquitectura y Tecnología de Computadores |
Fecha de publicación: | 30-jun-2020 |
Fecha de lectura: | 25-jun-2020 |
Resumen: | In this project, we propose an action prediction and a data generation pipeline. While, the former makes use of Deep Learning, the latter results in a pipeline that makes possible the generation of real and synthetic data. Moreover, to feed the deep learning method a large amount of annotated data is needed. For this purpose an action tagging tool is also featured. Furthermore, in order to supply the lack of data, we have also proposed a video data augmentation pipeline for action recognition purposes. While the 3DPLab team developed a photorealistic synthetic data generator called UnrealRox, we will use this system working with some sequences recorded with a mocap to generate the necessary synthetic data. We have generated a total of 5 different useful sequences with a complex setup of 3 kinects and a capture motion suit. Finally, we have deployed and tested the novel Temporal Segment Network with the state of the art Action Recognition dataset UCF-101. |
URI: | http://hdl.handle.net/10045/107802 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/bachelorThesis |
Derechos: | Licencia Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 |
Aparece en las colecciones: | Grado en Ingeniería Informática - Trabajos Fin de Grado |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
A_Framework_to_Generate_and_Label_SyntheticReal_Video_D_Allhoff__Daniel_Finn.pdf | 12,01 MB | Adobe PDF | Abrir Vista previa | |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.