计算机工程 ›› 2019, Vol. 45 ›› Issue (4): 267-274.doi: 10.19678/j.issn.1000-3428.0050099

• 图形图像处理 • 上一篇    下一篇

基于改进FOA-SVM的矿井火灾图像识别

苗续芝1,陈伟1,毕方明1,房卫东2,张武雄2   

  1. 1.中国矿业大学 计算机科学与技术学院,江苏 徐州 221116; 2.中国科学院上海微系统与信息技术研究所 无线传感网与通信重点实验室,上海 201899
  • 收稿日期:2018-01-15 出版日期:2019-04-15 发布日期:2019-04-15
  • 作者简介:苗续芝(1992—),女,硕士研究生,主研方向为图像处理、信息安全;陈伟,教授;毕方明,副教授;房卫东,高级工程师、博士;张武雄,博士。
  • 基金项目:

    国家自然科学基金(51104157);国家自然科学基金联合基金项目(U1510115);中国博士后科学基金(2016M601910);中国博士后科学基金特别项目(2013T60574);江苏省基础研究计划(BK20140202)。

Mine Fire Image Recognition Based on Improved FOA-SVM

MIAO Xuzhi1,CHEN Wei1,BI Fangming1,FANG Weidong2,ZHANG Wuxiong2   

  1. 1.School of Computer Science and Technology,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China; 2.Key Laboratory of Wireless Sensor Network and Communication,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai 201899,China
  • Received:2018-01-15 Online:2019-04-15 Published:2019-04-15

摘要:

为解决矿井下传统火灾识别方法准确率较低的问题,提出一种基于改进果蝇优化算法(FOA)-支持向量机(SVM)的火灾图像识别算法。利用YCrCb颜色空间对捕获的图像进行分割,根据早期的火灾图像特征从图像序列中提取多个火灾特征值。用基于分群体融合的改进FOA算法搜索SVM最优核参数和惩罚因子,将提取的火灾图像特征值作为SVM的输入对样本数据进行分类。实验结果表明,采用该方法对矿井火灾进行识别时准确率达97.2%,其分类效果显著优于FOA方法、粒子群优化算法等。

关键词: 矿井火灾, 火灾特征, 图像处理, 支持向量机, 果蝇优化算法

Abstract:

In order to solve the problem of low accuracy of traditional fire recognition methods in underground mine,a fire image recognition algorithm based on improved Fruit Fly Optimization Algorithm(FOA)-Support Vector Machine(SVM) is proposed.YCrCb color space is used to segment the captured image,and several fire eigenvalues are extracted from the image sequence according to the early fire image features.The improved FOA algorithm based on group fusion is used to search the optimal kernel parameters and penalty factors of SVM,and the extracted fire image eigenvalues are used as the input of SVM to classify the sample data.Experimental results show that the accuracy of this method is 97.2%,and its classification effect is significantly better than FOA method and Particle Swarm Optimization(PSO) algorithm.

Key words: mine fire, fire features, image processing, Support Vector Machine(SVM), Fruit Fly Optimization Algorithm(FOA)

中图分类号: