Giter Club home page Giter Club logo

muii-tfm's Introduction

Trabajo Fin de Máster MUII - UAH

Título

Diseño, implementación y evaluación de una estrategia de detección de objetos abandonados en aplicaciones de videovigilancia

Resumen

Este trabajo plantea el estudio e implementación de algoritmos de aprendizaje profundo Deep Learning con la finalidad de detectar objetos abandonados en aplicaciones de videovigilancia.

Se ha realizado un estudio teórico de los algoritmos de detección y seguimiento disponibles en el Estado del Arte. Para la detección de objetos en tiempo real se ha empleado YOLOv4. Como algoritmo de seguimiento se ha optado por Deep SORT. Por último, se ha desarrollado un algoritmo que determine si un objeto ha sido abandonado o no. Todos ellos han sido implementados sobre el dataset de referencia MS COCO y evaluados sobre los datasets más relevantes en la detección de objetos abandonados como son GBA2018, PETS2007, AVSSAB2007 o ABODA.

Palabras clave: Deep Learning, YOLOv4, Deep SORT, videovigilancia, visión por computador.

Abstract

This Master's Thesis proposes the study and implementation of Deep Learning algorithms in order to detect abandoned objects in video surveillance applications.

A theoretical study of the detection and monitoring algorithms available in the State of the Art has been carried out. YOLOv4 has been used to detect objects in real time. Deep SORT has been chosen as tracking algorithm. Finally, an algorithm has been developed to determine when an object has been abandoned or not. All of them have been implemented on the MS COCO benchmark dataset and evaluated on the most relevant datasets in the detection of abandoned objects such as GBA2018, PETS2007, AVSSAB2007 or ABODA.

Keywords: Deep Learning, YOLOv4, Deep SORT, Video Surveillance, Computer Vision.

muii-tfm's People

Contributors

jmudy avatar

Stargazers

 avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.