Anzeige
Erschienen in:
2016 | OriginalPaper | Buchkapitel
Smoke Detection in Environmental Regions by Means of Computer Vision
verfasst von : Douglas A. G. Vieira, Adriano L. Santos, Hani C. Yehia, Adriano C. Lisboa, Carlos A. M. Nascimento
Erschienen in: Combinations of Intelligent Methods and Applications
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
This paper presents a novel method for smoke detection in videos based on three main steps: background removal, color classification, and temporal/spatial persistence. First, the regions of interest are determined by detecting objects in movement through background subtraction. After that, the moving objects are classified according to their color. Only objects with smoke colors are analyzed by the last stage, which carries out analysis of space movement, verifying the temporal persistence of pixels of interest in the video frames. Pixels that satisfy the rules defined in the three stages are considered pixels of smoke. The system considered in this work is compared with other existing systems, through tests with a database of videos that contains smoke images and videos that do not contain smoke images, but contain objects that look like smoke.