Real Time Fire detection and Localization in Video sequences using Deep Learning framework for Smart Building. Issue 1 (May 2021)

• Record Type: Journal Article
• Authors: Sridhar, P; Sathiya, R R
• Is Part Of: Journal of physics. Volume 1916:Issue 1(2021)
• Publication Date: 2021-05
• Subjects: fire detection -- Building environment -- Computer vision -- Deep learning frame work -- surveillance video; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1916/1/012027
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: This work presents autonomous electrical fire-detection and localization using computer vision based techniques. The proposed work uses YOLO v2 to extract the electrical fire features more effectively than other conventional and machine learning approaches. This working model is tested on commercial and residential building as well as indoor and outdoor environments. This framework has achieved high detection accuracy and low false alarm rate. Besides, the proposed frame work can be used for early real-time electrical fire detection in surveillance videos and we present experimental results for electrical fire localization in CCTV footage using the deep learning architecture proposed in this work.