基于气体形状特征和灰度分布的气体泄漏检测算法  

Gas leak detection algorithm based on gas shape features and grayscale distribution

作　　者：潘新雨 马燕[1] PAN Xinyu;MA Yan(College of Information,Shanghai Normal University,Shanghai 200234,China)

机构地区：[1]上海师范大学信息与机电工程学院,上海200234

出　　处：《智能计算机与应用》2023年第9期13-16,24,共5页Intelligent Computer and Applications

基　　金：国家自然科学基金(61373004)。

摘　　要：由于红外视频具有对比度低,信噪比低和边缘模糊等特点,在识别泄露气体时容易出现误判。为解决该问题,本文提出了基于气体形状特征和灰度分布的气体泄漏检测算法。首先,利用高斯滤波对红外视频作去噪处理;其次,利用背景减除法提取疑似气体泄露区域;提取各连通区域的形状特征向量,根据当前帧及其相邻帧间形状特征向量间的余弦相似度,排除非气体区域;最后,根据气体扩散过程中图像灰度变化特点,对上、下、左、右4条连线上的点利用最小二乘法进行直线拟合,再根据直线斜率确定气体泄漏区域。实验结果表明,本文提出的算法能准确地检测气体泄漏区域,对于视频中的干扰因素具有鲁棒性。Due to the characteristics of low contrast,low signal-to-noise ratio,and blurred edges of infrared video,it is easy to be misjudged when identifying leaking gas.To solve this problem,a gas leak detection algorithm based on gas shape features and grayscale distribution is proposed.Firstly,the infrared video is denoised by Gaussian filtering;secondly,the suspected gas leak region is extracted by background subtraction;then,the shape feature vectors of each connected region are extracted,and the nongas region is excluded according to the cosine similarity between the shape feature vectors of the current frame and its neighboring frames;finally,according to the characteristics of image grayscale change during gas diffusion,the straight lines are respectively fitted to the points on the top,bottom,left and right connecting lines using the least squares method,and then the gas leak region is determined according to the slope of the straight lines.The experimental results show that the proposed algorithm can accurately detect the gas leakage area and is robust to the interference factors in the video.

关 键 词：高斯滤波 气体泄漏检测 余弦相似度 最小二乘法 红外视频 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]