Fire detection for video surveillance applications using ICA K-medoids-based color model and efficient spatio-temporal visual features
作者：
Highlights：
• A computer vision-based fire detection method is presented.
• A robust color model is developed to reliably detect all candidate fire regions.
• A motion-intensity-aware motion detection technique is used to analyze the motion.
• Spatio-temporal features are used to distinguish real-fire from non-real regions.
• The performance is higher than that of the competitors.
摘要
•A computer vision-based fire detection method is presented.•A robust color model is developed to reliably detect all candidate fire regions.•A motion-intensity-aware motion detection technique is used to analyze the motion.•Spatio-temporal features are used to distinguish real-fire from non-real regions.•The performance is higher than that of the competitors.
论文关键词：Fire detection,Flame detection,Video surveillance,Video processing,Spatio-temporal features
论文评审过程：Received 15 November 2018, Revised 9 April 2019, Accepted 9 April 2019, Available online 10 April 2019, Version of Record 15 April 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.04.019
