Centroiding and Connected Component Labeling for Radar Images Using Image Processing Algorithms

R. M., Sridhara S.B, Anughna N, Anne Gowda A B, V. Patil
{"title":"Centroiding and Connected Component Labeling for Radar Images Using Image Processing Algorithms","authors":"R. M., Sridhara S.B, Anughna N, Anne Gowda A B, V. Patil","doi":"10.1109/ICSTCEE49637.2020.9277394","DOIUrl":null,"url":null,"abstract":"The main objective of this paper is to identify centroids for the given image using connected component labeling technique. Imaging radars are used to acquire the images of the required target and it produces 2D images. The imaging radar used here is wall penetrating radar which explores the targets behind the wall. The images obtained from this imaging radar are subjected to some processes like thresholding and filtering in order to improve the image characteristics. The region of interest is then defined using a technique called connected component labeling where the image is scanned and the pixels grouped into components based on pixel connectivity. All the pixels in the connected component of an image exhibit same pixel intensity values which are connected together. When all the groups in an image have been identified then each pixel will be labeled with a gray level or color labeling based on the component it was specified. Finally, these individually identified objects are located with centroid, these centroids show the presence of the targets. The main goal is to remove noise/clutters in an image in an efficient manner and to locate individual object in an image by a single point called centroid.","PeriodicalId":113845,"journal":{"name":"2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSTCEE49637.2020.9277394","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

The main objective of this paper is to identify centroids for the given image using connected component labeling technique. Imaging radars are used to acquire the images of the required target and it produces 2D images. The imaging radar used here is wall penetrating radar which explores the targets behind the wall. The images obtained from this imaging radar are subjected to some processes like thresholding and filtering in order to improve the image characteristics. The region of interest is then defined using a technique called connected component labeling where the image is scanned and the pixels grouped into components based on pixel connectivity. All the pixels in the connected component of an image exhibit same pixel intensity values which are connected together. When all the groups in an image have been identified then each pixel will be labeled with a gray level or color labeling based on the component it was specified. Finally, these individually identified objects are located with centroid, these centroids show the presence of the targets. The main goal is to remove noise/clutters in an image in an efficient manner and to locate individual object in an image by a single point called centroid.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于图像处理算法的雷达图像质心和连通分量标记
本文的主要目的是利用连通分量标记技术来识别给定图像的质心。成像雷达用于获取所需目标的图像并产生二维图像。这里使用的成像雷达是穿墙雷达,探测墙后的目标。该成像雷达得到的图像经过阈值化和滤波处理,以改善图像特性。然后使用一种称为连通分量标记的技术定义感兴趣的区域,其中扫描图像并根据像素连通性将像素分组为组件。图像的连接分量中的所有像素显示连接在一起的相同像素强度值。当图像中的所有组都被识别后,每个像素将被标记为基于它被指定的组件的灰度或颜色标签。最后,用质心对这些单独识别的目标进行定位,这些质心表示目标的存在。主要目标是以一种有效的方式去除图像中的噪声/杂波,并通过称为质心的单个点定位图像中的单个物体。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Flower Classification using Deep Learning models An Unprecedented PSO-PID Optimized Glucose Homeostasis Improving elasticity in cloud with predictive algorithms A Second Order-Second Order Generalized Integrator for Three - Phase Single – Stage Multifunctional Grid-Connected SPV System Continuous Compliance model for Hybrid Multi-Cloud through Self-Service Orchestrator
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1