Computer vision based method for real-time fire and flame detection

By B. Töreyin, Yigithan Dedeoglu, U. Güdükbay, A. Çetin. Pattern Recognition Letters, 2006

678 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/957934498e77402e20474b348454bd0fb3966028

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Risk, Reliability and Quality

Citations in the corpus

A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing (2020, methodology): “Local Very high spatial resolution (centimeters) depending on camera resolution and distance between the camera and the event Limited coverage depending the specific task of each system 85%–100% [35,40,58,60] IR Infrared spectrum”
A framework for use of wireless sensor networks in forest fire detection and monitoring (2012, background): “In case of fire or smoke activity, the cameras and detectors sense this abnormal event and report it to a control center (Aerovision Web Page, 2011; B.C. Fire Lookout Towers , 2011; Toreyin, Dedeoglu, Gudukbay, & Cetin, 2006).”
Video fire detection - Review (2013, methodology): “Using range filters [24], variance/histogram analysis [32], or spatial wavelet analysis [13,28], the spatial color variations in pixel values are analyzed to distinguish ordinary fire-colored objects from uncontrolled fires.”
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, methodology): “Several fire detection systems [357][299][133][122] use in their first step background subtraction to detect moving pixels.”
Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications (2019, methodology): “[17] used temporal and spatial wavelet 82 analysis to determine fire and nonfire regions.”
Convolutional Neural Networks Based Fire Detection in Surveillance Videos (2018, methodology): “Compared to pixel-level methods, blob-level flame detection methods [7] show better performance as such methods consider blob-level candidates for features extraction to detect flame.”
A Forest Fire Detection System Based on Ensemble Learning (2021, methodology): “[10] used 1D temporal wavelet transform to detect flame flicker, and applied 2D spatial wavelet transform to identify fire moving regions.”