基于多传感器信息融合的路面等级识别研究  

Research on Road Profile Classification Based on Multi-sensor Information Fusion

作　　者：胡益谦 赵丰 HU Yi-qian ZHAO Feng(PLA 96271 troops, Luoyang China, 471600 Beijing Institute of Aerospaee Control Devices, Beijing 100854)

机构地区：[1]中国人民解放军96271部队 [2]北京航天控制仪器研究所

出　　处：《车辆与动力技术》2017年第3期15-19,共5页Vehicle & Power Technology

摘　　要：针对车辆行驶路面等级识别的问题,通过采集与融合多种传感器的信号数据,提出一种基于小波包和经验模态分解(EMD)协同信号处理方法.通过最大相关最小冗余(MRMR)算法对特征子集进行优化,优质特征子集将进入概率神经网络分类器(PNN)与随机森林分类器组成的级联分类器进行训练与测试,得到最终路面等级分类结果.仿真结果显示,与使用单一传感器进行路面等级识别相比,分类结果正确率得到有效提高.In order to slove the road ranking recoginition problem,a cooperated signal processing method based on wavelet packet and empirical mode decomposition（ EMD） is used. After extracting the statistical characteristics of the signal,the feature subset is optimized by the maximum correlation minimum redundancy（ MRMR） algorithm. The high quality feature subset will be the input of the PNN and random forest classifier for training and testing, and then the final road classification results are achiedved. Simulation results show that the accuracy of the classification results is improved compared with the results obtaned from the single level sensor.

关 键 词：路面等级 信息融合 神经网络 

分 类 号：U461.4[机械工程—车辆工程]