Image-based Real-Time Fire Detection Using Deep Learning with Data Augmentation for Vision-based Surveillance Applications

被引：12

作者：

Kang, Li-Wei ^{[1
]}

Wang, I-Shan ^{[2
]}

Chou, Ke-Lin ^{[2
]}

Chen, Shih-Yu ^{[2
]}

Chang, Chuan-Yu ^{[2
]}

机构：

[1] Natl Taiwan Normal Univ, Dept Elect Engn, Taipei, Taiwan

[2] Natl Yunlin Univ Sci & Technol, Dept Comp Sci & Informat Engn, Touliu, Yunlin, Taiwan

来源：

2019 16TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS) | 2019年

关键词：

D O I：

10.1109/avss.2019.8909899

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

With recent advances in embedded processing capability, vision-based real-time fire detection has been enabled in surveillance devices. This paper presents an image-based fire detection framework based on deep learning. The key is to learn a fire detector relying on tiny-YOLO (You Only Look Once) v3 deep model. With the advantage of lightweight architecture of tiny-YOLOv3 and training data augmentation by some parameter adjusting, our fire detection model can achieve better detection accuracy in real-time with lower complexity in the training stage. Experimental results have verified the effectiveness of the proposed framework.

引用

页数：4