随机抽样一致性算法在Vondrak滤波中的应用  

Application of Random Sample Consensus Algorithm in Vondrak Filtering

作　　者：王逸凡 彭良福[1] 陈子豪 WANG Yifan;PENG Liangfu;CHEN Zihao(College of Electrical&Information Engineering,Southwest Minzu University,Chengdu 610041,China)

机构地区：[1]西南民族大学电气信息工程学院,成都610041

出　　处：《电讯技术》2020年第5期591-595,共5页Telecommunication Engineering

基　　金：西南民族大学研究生创新型科研项目(CX2019SZ25)。

摘　　要：针对传统Vondrak滤波法易受粗差值影响的问题,提出了一种基于随机抽样一致性的Vondrak滤波算法来探测和剔除数据中的粗差。首先通过采用随机抽样一致性算法对需要滤波的观测数据进行预处理;然后对数据是否在阈值范围内进行判断,给相应的数据赋予不同的权值系数;最后利用Vondrak滤波估计预处理后的数据。为了验证所提滤波算法的有效性,通过计算机仿真的方法,采用两种不同的信号模型产生信号,并且在两种信号中都加入粗差,分别利用传统的Vondrak滤波、抗差Vondrak滤波和所提滤波算法对两种信号进行滤波。仿真结果表明,所提滤波算法具有良好的粗差探测能力。For the problem that the traditional Vondrak filtering is susceptible to the gross errors,the Vordrak filtering based on random sample consensus is proposed to detect and eliminate the gross errors in the data.Firstly,the random sample consensus is used to preprocess the observation data that needs to be filtered.Then by judging whether the data is within the threshold,different weights are assigned to the corresponding data.Finally,the estimation of the preprocessed data is obtained by the Vondrak filtering.In order to verify the effectiveness of the proposed filtering algorithm,two different signal models are used to generate the signal by computer simulation,and the gross errors are added to both signals. Both signals are filtered with traditional Vondrak filtering,robust Vondrak filtering,and proposed filtering algorithm.Results of computer simulation show that the proposed filtering algorithm has good detection capability of gross errors.

关 键 词：VONDRAK滤波 随机抽样一致性 数据处理 粗差探测 

分 类 号：TN713[电子电信—电路与系统]