光感传感器的视频监控系统斑点特征提取研究  

Research on speckle feature extraction of video surveillance system based on light sensor

作　　者：易文平 郑瑞卿 YI Wenping;ZHENG Ruiqing(Center of Network and Education Technology,Yichun University,Yichun Jiangxi 336000,China)

机构地区：[1]宜春学院网络与教育技术中心,江西宜春336000

出　　处：《激光杂志》2021年第11期201-205,共5页Laser Journal

基　　金：江西省教育厅科技课题(No.GJJ181553)、江西省横向课题(No.HX2019WL0143)。

摘　　要：为解决实际提取视频监控系统斑点特征时,视频图像背景元素与斑点间产生混淆,导致斑点特征与背景元素间的相似性过大的问题,研究一种光感传感器的视频监控系统斑点特征提取方法。定义视频图像内的背景信息后,挖掘光感传感器斑点特征信息,整合斑点特征信息为一个集合,逆变换处理重建视频监控系统中的分辨率,等效处理斑点各项信息为统一的计量尺度,设定一个时频脊线参数,控制视频图像内的背景元素与斑点特征间的差异性。设计对比实验,实验结果表明:设计的特征提取方法得到的相似性数值最小,在0.2左右。In order to solve the problem that the similarity between the background elements and the background elements is too large when extracting the speckle features of video surveillance system,a speckle feature extraction method of video surveillance system based on light sensor is studied.After defining the background information in the video image,the spot feature information of the light sensor is mined,and the spot feature information is integrated into a set.The resolution in the video monitoring system is reconstructed by inverse transformation.Each information of the speckle is treated as a unified metric.A time-frequency ridge parameter is set to control the difference between the background elements and the speckle features in the video image.The experimental results show that the similarity value obtained by the feature extraction method designed in this paper is the smallest,about 0.2.

关 键 词：光感传感器 视频监控系统 斑点特征 相似性数值 

分 类 号：TN929[电子电信—通信与信息系统]