Abstract

COTA, A. et al. Visual automatic fire detection through the Histogram of Oriented Gradients and Support Vector Machine. Rev Inv Tec [online]. 2016, vol.4, n.1, pp. 90-98. ISSN 2306-0522.

Abstract The visual detection ofobjects in digital images, is one ofthe challenging issues in Computer Science, especially ifthose objects do not have a definite shape, as in the case offire. To meet the challenge, it is necessary to use techniques Computer Vision and Machine Learning, so that the results are approximate as much as possible, to the human visual system. Given a digital image, with the aim of identifying areas where fire there, the computer should locate exactly the same areas as a human would. For a human, the task ofobject detection does not involve much difficulty for the computer instead is a really difficult task, since, fire and environments which could manifest itselfare infinitely variable. The importance of automation in the visual detection offire, lies in the practical application that can be given, for example, the product obtained implanted in the computer of a drone, would cover more territory for monitoring demonstrations offire inforest areas. In this article, implementation and evaluation of techniques Computer Vision and Automatic for the automation of visual detection offire in forest areas described learning.

Keywords : fire detection; computer vision; machine learning; HOG; SVM.