使用健壮的AdaBoost进行基于视频的火灾烟雾检测 （英文论文翻译）

---

英文版论文原文：[https://www.ncbi.nlm.nih.gov/pubmed/30400645](https://www.ncbi.nlm.nih.gov/pubmed/30400645

---

使用健壮的AdaBoost进行基于视频的火灾烟雾检测。

A Video Based Fire Smoke Detection Using Robust AdaBoost

Xuehui Wu, Xiaobo Lu& Henry Leung

• 东南大学自动化学院，江苏南京210096； xhwu@seu.edu.cn

• School of Automation, Southeast University, Nanjing 210096, China; xhwu@seu.edu.cn

• 东南大学教育部复杂工程测量与控制教育部重点实验室，南京210096

• Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing 210096, China

• 2500大学卡尔加里大学电气与计算机工程系加拿大卡尔加里西北大学博士，AB T2N 1N4； lenugh@ucalgary.ca

• Department of Electrical and Computer Engineering, University of Calgary, 2500 University Dr N.W Calgary, AB T2N 1N4, Canada; lenugh@ucalgary.ca

Abstract

这项工作考虑使用摄像头传感器检测火灾烟雾。 从火烟中提取静态特征（包括纹理，小波，颜色，边缘方向直方图，不规则性）以及动态特征（包括运动方向，运动方向的变化和运动速度），以不同的组合进行训练和测试。 提出了一种鲁棒的AdaBoost（RAB）分类器，以提高训练和分类的准确性。 在众所周知的具有挑战性的数据集上进行的大量实验及其在火灾烟雾检测中的应用表明，提出的火灾烟雾检测器具有令人满意的性能。

This work considers using camera sensors to detect fire smoke. Static features including texture, wavelet, color, edge orientation histogram, irregularity, and dynamic features including motion direction, change of motion direction and motion speed, are extracted from fire smoke to train and test with different combinations. A robust AdaBoost (RAB) classifier is proposed to improve training and classification accuracy. Extensive experiments on well known challenging datasets and application for fire smoke detection demonstrate that the proposed fire smoke detector leads to a satisfactory performance.

1. Introduction

早期发现火灾烟雾由于其对社会保障和经济发展的重要性，近来引起了很多关注。 传统的点烟感烟探测器传感器对于室内应用是有效的，但是它们很难在大型室外区域中探测烟雾，这是因为点烟感烟探测器通常会通过电离来检测烟雾和火产生的某些颗粒的存在[1]，光度法 [2]或烟雾温度[3,4]。 它们需要靠近火和烟，这对于露天场所无效。 为了使颗粒到达这些传感器以激活警报，需要许多传感器来覆盖大面积，这并不划算。

Detection fire smoke at the early stage has drawn a lot of attentions recently due to its importance to social security and economic development. Conventional point fire smoke detector sensors are effective for indoor applications, but they have difficulties to detect smoke in large outdoor areas, it is because point fire smoke detector typically detect the presence of certain particles generated by smoke and fire by ionization [1], photometry [2], or smoke temperature [3,4]. They require a close proximity to fire and smoke, which are not effective for open spaces. For particles to reach these sensors to activate alarms, many sensors are needed to cover a large area which is not cost effective.

使用摄像机进行基于视频的火灾烟雾探测在大空间和开放空间中引起了极大的兴趣[5]。迄今为止，闭路电视（CCTV）监视系统已广泛安装在许多公共场所。如果系统中安装了可靠的火灾探测软件，则这些系统可用于提供早期火灾烟雾探测。 Gottuk等。 [6]在船上场景中，针对常规现场系统测试了三种基于市售视频的火灾探测系统。发现基于视频的系统在火焰检测中更有效。这些系统在经济上可行，因为CCTV摄像机已经可用于交通监控[7]和监视[8]应用。 Braovic，M等。 [9]提出了一种用于对自然景观图像上的区域进行快速分割和分类的专家系统，该系统适用于实时自动野火监测和监视系统。需要注意的是，在大多数室外场景中，烟雾在燃烧前总是可见的。这促使我们进行研究，以从单个视频帧中检测是否存在火焰的烟雾。

Video based fire smoke detection using cameras is of great interest in large and open spaces [5]. Closed circuit television (CCTV) surveillance systems are widely installed in many public areas to date. These systems can be used to provide early fire smoke detection if a reliable fire detection software is installed in the system. Gottuk et al. [6] test three commercially available video based fire detection systems against conventional spot systems in a shipboard scenario. Video based systems are found to be more effective in flame detection. These systems are economically viable as CCTV cameras are already available for traffic monitoring [7] and surveillance [8] applications. Braovic, M et al. [9] propose an expert system for fast segmentation and classification of regions on natural landscape images that is suitable for real-time automatic wildfire monitoring and surveillance systems. It is noted that smoke is always visible before fire in most outdoor scenarios. This motivates us to research on detecting smoke in the absence or presence of flame from a single frame of video.

基于视频的火灾烟雾检测存在一些技术挑战。 首先，就误报率而言，它不如基于粒子采样的检测器。 这主要归因于烟雾浓度，场景照明，干扰物体的变化。 二次烟雾和火灾很难建模，大多数现有图像处理方法不能很好地表征烟雾[10]。 当前的火灾探测算法是基于视频中静态和运动信息的使用来探测火焰[11-15]。 为了降低误报率和漏检率，已经做出了许多努力。 表1显示了这些方法中使用的一些静态和动态功能。 如图所示，最常用的功能是颜色，纹理，能量和动态功能。

There are some technical challenges in video based fire smoke detection. First, it is observed to be inferior to particle-sampling based detectors in terms of false alarm rate. It is mainly due to the variability in smoke density, scene illumination, interfering objects. Second smoke and fire are difficult to be modeled, most of the existing image processing methods do not characterize smoke well [10]. Current fire detection algorithms are based on the use of static and motion information in video to detect flames [11–15]. Many efforts have been made to reduce the false alarm rate and missing detection rate. Table 1 shows some static and dynamic features used in these approaches. As shown, the most used features are color, texture, energy and dynamic features.

表1.有关火灾烟雾特征提取的文献。

Table 1. Literatures about fire smoke feature extraction.

另一方面，对于分类，一些研究人员[15,16,18-22]使用提取的特征分析中的阈值或参数，这比较省时，但在某些复杂的环境中无法适应。 其他一些研究人员[30,31]使用著名的AdaBoost训练模型并进行分类。 基于AdaBoost的组件分类器可以以较高的精度相对解决过拟合问题，而组件分类器的一个弱分类器是学习器，它可以返回大致胜过随机猜测的假设。 对于组件分类器，它们在每个步骤中的权重更新主要取决于最后的错误，

On the other side, for classification, some researchers [15,16,18–22] use thresholds or parameters from analysis of extracted features, which is less time-consuming but not adaptive in some complex environments. Some other researchers [30,31] use well known AdaBoost to training models and classify. AdaBoost based component classifiers can solve the overfitting problem relatively with high precision, one weak classifier of component classifiers is a learner which can return a hypothesis that roughly outperform random guessing. For the component classifiers, the weights updates of them in every step mainly depend on the last errors,

$${\alpha }_m=\frac{1}{2}ln\frac{1-e_m}{e_m}\text{\hspace{1em}(1)}$$

${\alpha }_m$ 给出了组件分类器的权重，而 $e_m$ 是错误。 当然，权重 ${\alpha }_m$ 应该为正，因此误差 $e_m$ 必须小于0.5，AdaBoost也要求误差不少于0.5，以便boosting函数可以理解这些级联分类器 。 因此，我们必须选择一系列适当的基本分类器，并谨慎地为每个基本分类器设置一个最佳参数，这也很费时。

${\alpha }_m$ gives the weights of component classifiers, and $e_m$ is the errors. Definitely, the weights ${\alpha }_m$ should be positive, so the error $e_m$ is required to be less than 0.5, and AdaBoost also requires the error not much less than 0.5, so that the boosting function can make sense of these cascade classifiers. Therefore, we must select a series of proper base classifiers and set a best parameter for every base classifier prudently and it is also time-consuming.

深度学习也被认为可以检测烟雾。 在[32]中，使用带级卷积神经网络（CNN）火灾检测器从头开始，第二次学习和分类，使用带注释的补丁训练二进制分类器。 穆罕默德等。 [33]提出了一种用于火灾烟雾检测的自适应优先机制。 CNN和用于灾难管理的多媒体物联网（IoMT）用于早期火灾探测框架。 通过深度学习，可以自动学习功能。 但是，这些用于火灾烟雾检测的深度学习方法仍然受到学习静态特征的限制。 Wu等。 [34]结合深度学习方法和常规特征提取方法来识别火灾烟雾区域。 CNN用于Caffe框架中以实现具有静态功能的Caffe模型。 这种深度学习方法在一定程度上可以很好地发挥作用，但是动态功能并未针对大多数情况直接进行训练。

Deep learning is also considered for smoke fire detection. In [32], a binary classifier is trained using annotated patches from scratch, second, learning and classification using cascade convolutional neural network (CNN) fire detector. Muhammad et al. [33] propose an adaptive prioritization mechanism for fire smoke detection. CNN and the internet of multimedia things (IoMT) for disaster management are used for early fire detection framework. Through deep learning, features can be learned automatically. However, these deep learning methods for fire smoke detection are still limited by learning static features. Wu et al. [34] combine deep learning method and conventional feature extraction method to recognize the fire smoke areas. CNN is used in Caffe framework to achieve a Caffemodel with static features. This deep learning approach can work well to certain extent, but the