Git Product home page Git Product logo

pi-most's Introduction

Image and video processing with application to environmental sciences

Final Project of BSc Informatics Engineering

Abstract

Every year, several countries are haunted by forest fires that sometimes can take proportions out of the reach areas of firefighters. In the hottest months as July, August and September there is a high probability of fire breaking out, and in 2018 just in Portugal, 9725 rural fires were recorded during this period. These fires are responsible for the emission of large amounts of gases into the atmosphere.

The main aim of this project is to extract data on the spread of outbreaks of forest fires in order to calculate the emission of gases to the atmosphere and its burned area. This way, several images and videos were collected using a drone that flew over a burning land. Posteriorly our system is able to segment the burned regions by defining the areas of interest and non interest in order to create polygons that match to temporally burned regions. After obtaining these values, operations are performed on these images in order to match those same polygons to georeferenced regions and thus obtain a real burned area and its propagation.

The final phase of the whole process is the creation of two distinct shapefiles, one for visualization / animation for the end user of the propagation of the different foci and another for incorporation in a software along with other significant data in order to calculate the emissions of gases to the atmosphere.

Resumo

Todos os anos, diversos países são assombrados por incêndios florestais que por vezes podem tomar proporções fora do alcance dos bombeiros. Nos meses de maior calor, como Julho, Agosto e Setembro existe uma grande probabilidade de deflagração de incêndios, e no ano de 2018, só em Portugal, foram contabilizados durante esse período 9725 incêndios rurais. Incêndios esses responsáveis pela emissão de grandes quantidades de gases para a atmosfera.

Este projeto tem como objetivo principal extrair dados relativamente à propagação de focos de incêndios florestais de modo a proceder ao cálculo de emissões de gases para a atmosfera e respetiva área ardida. Deste modo, foram recolhidas diversas imagens e vídeos com recurso a um drone que sobrevoava um terreno em chamas. Posteriormente o nosso sistema é capaz de segmentar as regiões ardidas através da definição das áreas de interesse e não interesse de modo a gerar polígonos que correspondem a regiões ardidas temporalmente. Depois de obter esses valores são feitas operações sobre essas imagens de modo a corresponder esses mesmos polígonos a regiões georreferenciadas e assim obter uma área real ardida e a sua propagação.

A fase final de todo o processo é a criação duas shapefiles distintas, uma com o objetivo de visualização/animação para o utilizador final da propagação dos diferentes focos e outra para a incorporação num software juntamente com outros dados significantes de modo a calcular as emissões de gases para a atmosfera.

Poster

poster

Authors

  • João Santos - joaocps
  • Vasco Marieiro
  • Henrique Manso
  • João Magalhães
  • Diego Trovisco

pi-most's People

Contributors

joaocps avatar

Watchers

 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.