电子测量与仪器学报

韦海成,王生营,许亚杰,赵静,肖明霞.样本熵融合聚类算法的森林火灾图像识别研究[J].电子测量与仪器学报,2020,34(1):171-177

样本熵融合聚类算法的森林火灾图像识别研究

Forest fire image recognition algorithm of sample entropy fusion and clustering

DOI：

英文关键词:fire image image recognition K-Means clustering sample entropy

基金项目:北方民族大学校级重点项目(2019KJ37)、宁夏自然科学基金(NZ17050)、国家自然科学基金(61861001)、教育部“天诚汇智”基金(2018A01016)、宁夏先进智能感知科技创新团队和北方民族大学智能感控与工业云技术校级重点实验室资助项目

作者	单位
韦海成	1.北方民族大学基础实验教学与工程实训中心
王生营	2.北方民族大学电气信息工程学院
许亚杰	2.北方民族大学电气信息工程学院
赵静	3.宁夏大学信息工程学院
肖明霞	2.北方民族大学电气信息工程学院

Author	Institution
Wei Haicheng	1. Basic Experimental Teaching and Engineering Training Center North Minzu University
Wang Shengying	2. School of Electrical and Information Engineering, North Minzu University
Xu Yajie	2. School of Electrical and Information Engineering, North Minzu University
Zhao Jing	3. School of Information Engineering, Ningxia University
Xiao Mingxia	2. School of Electrical and Information Engineering, North Minzu University

摘要点击次数: 333

全文下载次数: 0

中文摘要:

针对森林火灾图像识别中遇到的漏检和误检等问题，提出了一种基于K-Means聚类下样本熵值判别算法。算法先将采集到的森林火灾图像进行色域空间转换，降低了视觉偏差在图像识别过程中的影响。然后采用K-Means聚类算法，通过HSV分量的欧氏距离准则，对火灾预期出现的图像子集进行聚类。在此基础上，通过样本熵对聚类后的图像子集权重进行辨别，区分类火灾区域和火灾区域的熵值统计差异，确认聚类筛选出来的图像子集是否存在火灾。实验结果表明，采用样本熵融合K-Means聚类算法对森林火灾图像识别能够有效提高识别正确率。经过60幅图像的检测，全部图像的火灾区域识别正确率提高到96.67%，平均识别时间为16.03 s。由于本算法具有较强的鲁棒性和便捷性，能够适应复杂背景下火灾区域识别工作，相对于传统K-Means算法具有更好的检测效果。

英文摘要:

Aiming at the problems of missing and false detection encountered in image recognition on the forest fire, a sample entropy discrimination algorithm based on K-Means clustering was proposed. First, the collected forest fire images were transformed into color gamut space, which reduced the influence of visual deviation in the process of image recognition. Then, the K-Means clustering algorithm was adapted to cluster the image subset that was expected by fire through the Euclidean distance criterion of HSV components. On this basis, the weight of the clustered image subset was identified by using the sample entropy, the entropy values of the correlative fire regions and the real fire regions were statistically distinguished. Then it was confirmed whether there was a fire in the subset of images screened by the cluster. The experimental results showed that by using the sample entropy fusion K-Means clustering algorithm, the recognition accuracy can be effectively improved in forest fire image recognition. After the detection of 60 images, the correct identification rate of fire area in all images was improved to 96.67%, and the average identification time was 16.03 s. Due to the strong robustness and convenience of the algorithm, it is able to adapt to the identification of the fire area under complex background and has better detection effects than the traditional K-Means algorithm.

查看全文查看/发表评论下载PDF阅读器