Anzeige
Erschienen in:
2021 | OriginalPaper | Buchkapitel
An Efficient Fire Detection System Using Support Vector Machine and Deep Neural Network
verfasst von : Archana Venugopal, Febi Justin, Linju Santhosh, Riya Binny, NG Resmi
Erschienen in: Smart Technologies for Sustainable Development
Verlag: Springer Singapore
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Fire is a dangerous disaster. Uncontrollable fire can cause massive destruction to life and property. Hence fire detection and alarming is a crucial and ever-demanded topic. A fire alarm must be functionally capable and reliable. This paper mainly focuses on a real-time system for fire detection. Videos acquired from CCTVs or webcams are converted to a sequence of images which are then fed to the classifier. Upon detecting fire from the images extracted, an alert is sent to the authorities concerned. Support vector machine (SVM) and deep neural network are used to develop the proposed fire detection system. Both the algorithms are employed to build classification models. Their performances are then compared and the model which gives better accuracy is selected.