Characteristics Based Fire Detection System Under the Effect of Electric Fields With Improved Yolo-v4 and ViBe

To address slow image-based detection of fires under the effect electric fields and its limitation to static fire characteristics, this paper proffersa video-based system with improved you only look once version 4 (Yolo-v4) visual background extractor (ViBe) algorithms. The proposed uses a simplified weighted bi-directional feature pyramid network (Bi-FPN) in place path aggregation (PANet) as fusion Yolo-v4. Using multiple dynamic it can eliminate falsely detected frames. ViBe algorithm is consider sudden change light triggered by flickering. Compared other algorithms, achieves 98.9% accuracy false rate 2.2%. It extract target adjusting changes using no more than 16 Moreover, characteristics compared fields.