Clasificación de vídeos mediante Redes Neuronales Artificiales

[EN] Nowadays, the research on computer vision and machine learning is in its best moment. The computational capacity and communications currently available in any device, have risen new challenges. Among them, the task of human or object recognition on images and video are impulsed by the best univ...

Descripción completa

Detalles Bibliográficos
Autor: Jorge-Cano, Javier|||0000-0002-9279-6768
Tipo de recurso: tesis de maestría
Fecha de publicación:2015
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:español
OAI Identifier:oai:riunet.upv.es:10251/64848
Acceso en línea:https://riunet.upv.es/handle/10251/64848
Access Level:acceso abierto
Palabra clave:Visión por computador
Aprendizaje automático
Redes neuronales artificiales
Reconocimiento de la actividad humana
Computer vision
Machine learning
Artificial neural networks
Human activity recognition
LENGUAJES Y SISTEMAS INFORMATICOS
Máster Universitario en Inteligencia Artificial, Reconocimiento de Formas e Imagen Digital-Màster Universitari en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital
Descripción
Sumario:[EN] Nowadays, the research on computer vision and machine learning is in its best moment. The computational capacity and communications currently available in any device, have risen new challenges. Among them, the task of human or object recognition on images and video are impulsed by the best universities and technological companies. Concretely, human activity recognition in videos has a direct application in many environments: security systems, interaction analysis, illness identification, etc. For this reason, this project proposes a prospective study about the task of THUMOS competition on computer vision. In this task, it is required to classify videos by activity, among a set of 101 activities, belonging to 5 different kinds: Human-Human interaction, Human-Object interaction, sports, body-motion, and playing musical instruments. This thesis proposes, applied to this task for the first time, a model based on artificial neural networks that uses improved Dense Trajectories as a feature extraction technique. This thesis will analize the current state-of-the-art, and it will perform experiments in order to obtain the best model for this task, and afterwards, these experiments will be compared with the results provided by the approaches on the top ten of the THUMOS classification