Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Biblos-e Archivo
Bachelor thesis . 2016
Data sources: Biblos-e Archivo
versions View all 2 versions
addClaim

Seguimiento de objetos en vídeo a largo plazo

Authors: Maza Vargas, Borja;

Seguimiento de objetos en vídeo a largo plazo

Abstract

En este proyecto se propone un análisis del seguimiento de objetos en secuencias de largo plazo. Recientemente se han incrementado los desarrollos de algoritmos de seguimiento enfocados a vídeos de corta duración. Sin embargo ante la constante evolución de los trackers y del aumento en el tiempo de las secuencias de vídeo en el uso diario, surge la necesidad de estudiar mecanismos que mejoren los ya desarrollados y la creación de nuevos algoritmos destinados para tratar especialmente con secuencias de largo plazo. El objetivo principal del proyecto ha sido el estudio, diseño y evaluación de un algoritmo que combinase otros trackers desarrollados previamente tanto en secuencias de corto como de largo plazo. Para ello, en primer lugar se ha realizado un estudio del estado del arte en referencia al seguimiento de objetos, con especial atención en el caso de vídeos de largo plazo. Después el trabajo se centra en la selección y descripción de los algoritmos de seguimiento escogidos para evaluar y comparar el conjunto de vídeos de este proyecto. Una vez se han estudiado estos trackers, se avanza al diseño e implementación de un algoritmo de fusión. Esta propuesta pretende examinar el comportamiento de la combinación de algoritmo en el marco del largo plazo. Finalmente se procede a la evaluación del nuevo algoritmo sobre numerosas secuencias a fin de poder realizar una comparación con los algoritmos individuales. Debido a que las secuencias de largo plazo presentan un gran número de problemas, los resultados obtenidos en su mayoría por todos los trackers son relativamente bajos.

In this master thesis an analysis of tracking objects in long-term sequences is proposed. Recently, the development of video tracking algorithms has been focused on short videos. However, the need to operate for long times (e.g. 24/7 video-surveillance) have increased need to study mechanisms to improve and update existing tracking algorithms for their use in long-term sequences. The main aim of the project is the study, design and evaluation of an algorithm that combines other trackers sequences previously developed both short and long term. For this objective, first it has conducted a study of the state of art related to object tracking, focused on the case of long-term videos. After, this project focuses on the selection and description of the chosen tracking algorithms to evaluate and compare the set of videos of this project. Once these trackers have been studied, a fusion algorithm is implemented which examines the behavior of the combination of algorithm under the long-term framework. Finally this project proceeds to evaluate the combination-based algorithms on numerous sequences in order to make a comparison with the individual algorithms. Because long-term sequences have a large number of problems, the performance obtained mostly by all trackers are relatively low.

Country
Spain
Related Organizations
Keywords

Telecomunicaciones

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green