Deep Learning object detection architectures in ADAS

Otamendi Etxabe, Urtzi (2019). Deep Learning object detection architectures in ADAS. Thesis (Master thesis), E.T.S. de Ingenieros Informáticos (UPM).

Description

Title: Deep Learning object detection architectures in ADAS
Author/s:
  • Otamendi Etxabe, Urtzi
Contributor/s:
  • Baumela Molina, Luis
  • Gutierrez Basauri, Aitor
Item Type: Thesis (Master thesis)
Masters title: Inteligencia Artificial
Date: 2019
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (8MB) | Preview

Abstract

Los avances en la capacidad de cómputo y la existencia de grandes cantidades de datos han acelerado el avance en la aplicación de las técnicas de aprendizaje automático en diferentes campos. La robótica móvil, la conducción autónoma y los sistemas de Asistencia a la conducción, son claros exponentes de campos en los que la aplicación de la IA puede abrir nuevas oportunidades. En particular, las redes neuronales profundas, se están erigiendo como una delas técnicas más interesantes para la problemática de la percepción visual. El principal objetivo de este proyecto es el análisis de diferentes arquitecturas de redes neuronales para la detección en tiempo real de personas y objetos en el contexto de vehículos autónomos.---ABSTRACT---Advances in computing capacity and the existence of large quantities data have accelerated progress in the application of machine learning techniques in different fields. Mobile robotics, autonomous driving and driving assistance systems (ADAS) are clear exponents of fields in which the application of AI can open up new opportunities. In particular, deep neural networks are becoming one of the most interesting techniques for the problem of visual perception. The main objective of this project is the analysis of different neural network architectures for the real-time detection of people and objects associated with autonomous car mobility.

More information

Item ID: 58762
DC Identifier: http://oa.upm.es/58762/
OAI Identifier: oai:oa.upm.es:58762
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 06 Mar 2020 09:30
Last Modified: 06 Mar 2020 09:30
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM