Automatic Fire and Smoke Detection Method for Surveillance Systems Based on Dilated CNNs

Abstract

The technologies underlying fire and smoke detection systems play a crucial role in ensuring and delivering optimal performance in modern surveillance environments. In fact, fire can cause significant damage to lives and properties. Considering that the majority of cities have already installed camera-monitoring systems, this encouraged us to take advantage of the availability of these systems to develop cost-effective vision detection methods. However, this is a complex vision detection task from the perspective of deformations, unusual camera angles and viewpoints, and seasonal changes. To overcome these limitations, we propose a new method based on a deep learning approach, which uses a convolutional neural network that employs dilated convolutions. We evaluated our method by training and testing it on our custom-built dataset, which consists of images of fire and smoke that we collected from the internet and labeled manually. The performance of our method was compared with that of methods based on well-known state-of-the-art architectures. Our experimental results indicate that the classification performance and complexity of our method are superior. In addition, our method is designed to be well generalized for unseen data, which offers effective generalization and reduces the number of false alarms.

An Improvement of the Fire Detection and Classification Method Using YOLOv3 for Surveillance Systems

“…We used the results in their papers for comparison, but we are not sure whether they are true because source codes and datasets of these methods are not publicly available to check the real performance. We computed metrics such as F-measure (FM), precision, and recall, as in our earlier study [ 4 ]. The FM score is the weighted average that balances measurements between the means of precision and recall rates.…”

“…In our earlier work [ 4 ], we proposed a new fire detection method based on a DL approach, which uses a CNN that employs dilated convolutions. We evaluated our method by training and testing it on our custom-built dataset, which included the images of fire and smoke that we collected from the Internet and labeled manually.…”

“…Recent research has shown that computer vision and deep-learning-based techniques have achieved great success and play a vital role in the field of fire detection. In particular, computer vision and artificial intelligence (AI)-based methods, such as static and dynamic texture analysis [ 3 ], convolutional neural networks (CNNs) [ 4 ], and 360-degree sensors [ 5 ], have been commonly applied to fire detection environments.…”

Fire Detection Method in Smart City Environments Using a Deep-Learning-Based Approach

“…To evaluate and analyze the effectiveness of fire recognition cases, we compared the proposed approach with recently published fire detection methods. To perform this task, we employed widely used estimation metrics for object (static or dynamic) detection, as in our previous publications [16,56]. First, we computed the precision and recall metrics It employs a CSPNet strategy to partition the feature map of the base layer into two parts and subsequently merges them through a cross-stage hierarchy.…”

Video Processing Using Deep Learning Techniques: A Systematic Literature Review

“…The current era is full of technology and rolling on the digital revolution. A wide range of video processing applications is in entertainment [20], healthcare [21], retail [22][23],traffic management [24], transport [25], home automation [26][27], flame and smoke detection [28][29] [30],safety [31][32],and security [33]. These applications automatically generate the caption of the actions happening in the video sequence.…”