检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:柳革命 吴广裕 LIU Geming;WU Guangyu(School of Information Technology&Engineering,Guangzhou College of Commerce,Guangzhou Guangdong 511363,China)
机构地区:[1]广州商学院信息技术与工程学院,广东广州511363
出 处:《传感技术学报》2023年第6期937-942,共6页Chinese Journal of Sensors and Actuators
基 金:广州市科技计划项目(202002030230)。
摘 要:地磁检测技术因其低功耗、高性价比等特点,被认为是一种很好的路边车位车辆检测技术。但是由于抗干扰能力较弱,识别时的误报率较高,因此,当单独使用这一技术,应用上存在正确识别概率偏低的问题。基于地磁传感器的特性,提出了在检测单元上设置双组地磁传感器,利用其差分值确定多个判别特征,通过多层次的融合判断车辆的驶入、驶出状态的算法。设计了地磁差分检测系统,经过实验,表明该算法提高了系统的抗干扰能力,与单组地磁传感器阈值检测算法相比较,正确识别概率大幅度提高,达到98.0%,与基于地磁的双模检测技术的正确识别概率相当,取得了良好的车辆状态识别的效果。Because of the low power consumption and high cost performance,geomagnetic detection technology is considered as a good roadside parking vehicle detection technology.However,due to poor anti⁃interference ability,the false alarm rate of recognition is high.Therefore,when using this technology alone,there are problems in application.Based on the characteristics of geomagnetic sensors,an algorithm is proposed,which is realized through setting two groups of geomagnetic sensors on the detection unit,using the difference value to determine multiple discriminant features,and judging the vehicle entering and exiting state through multi⁃level fusion.A geomagnetic differential detection system is designed.The experimental results show that,compared with the threshold detection algorithm of single group of geomagnetic sensors,the algorithm improves the anti⁃interference ability,and the correct recognition probability is greatly improved,up to 98.0%,which is equivalent to the correct recognition probability of the dual⁃mode detection technology based on geomagnetic,achieving a good effect of recognizing the vehicle state on the roadside parking space.
关 键 词:地磁传感器 车辆检测 差分计算 路边车位 特征融合
分 类 号:TP164[自动化与计算机技术—控制理论与控制工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.33