Real-time video fire/smoke detection based on CNN in antifire surveillance systems
- PDF / 2,055,475 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 0 Downloads / 185 Views
ORIGINAL RESEARCH PAPER
Real‑time video fire/smoke detection based on CNN in antifire surveillance systems Sergio Saponara1 · Abdussalam Elhanashi1 · Alessio Gagliardi1 Received: 18 May 2020 / Accepted: 23 October 2020 © The Author(s) 2020
Abstract This work presents a real-time video-based fire and smoke detection using YOLOv2 Convolutional Neural Network (CNN) in antifire surveillance systems. YOLOv2 is designed with light-weight neural network architecture to account the requirements of embedded platforms. The training stage is processed off-line with indoor and outdoor fire and smoke image sets in different indoor and outdoor scenarios. Ground truth labeler app is used to generate the ground truth data from the training set. The trained model was tested and compared to the other state-of-the-art methods. We used a large scale of fire/smoke and negative videos in different environments, both indoor (e.g., a railway carriage, container, bus wagon, or home/office) or outdoor (e.g., storage or parking area). YOLOv2 is a better option compared to the other approaches for real-time fire/ smoke detection. This work has been deployed in a low-cost embedded device (Jetson Nano), which is composed of a single, fixed camera per scene, working in the visible spectral range. There are not specific requirements for the video camera. Hence, when the proposed solution is applied for safety on-board vehicles, or in transport infrastructures, or smart cities, the camera installed in closed-circuit television surveillance systems can be reused. The achieved experimental results show that the proposed solution is suitable for creating a smart and real-time video-surveillance system for fire/smoke detection. Keywords Video fire/smoke detection · Ground truth labeler · YOLOv2 · Embedded video systems · Real-time · CNN
1 Introduction Fire is one of the leading hazards endangering human life, the economy, and the environment [1]. Due to the rapid increase in fire accidents, every building or passenger vehicle for public transportation is equipped with fire protection and fire prevention systems. These systems consist mainly of point-type thermal and smoke detectors that need to be installed in proximity of the fire; otherwise, they may easily fail without detecting the fire. In addition, these devices must be properly installed and positioned as they can be damaged during the fire itself. Video-based fire detection is currently a standard technology due to image processing, computer vision, and Artificial Intelligence. These systems have remarkable potential advantages over traditional methods, such as a fast response and wide detection areas.
* Sergio Saponara [email protected] 1
Dip. Ingegneria Dell’Informazione, University of Pisa, Via G. Caruso 16, 56122 Pisa, Italy
Traditional smoke/fire sensors based on photometry, thermal, or chemical detection can react within several minutes, requiring a large amount of fire/smoke to trigger an alarm. Moreover, they cannot provide information about fire location and fire
Data Loading...
