模式识别在激光雷达图像分析识别中的应用  

Application of pattern recognition in laser radar image analysis recognition

作　　者：王小芬[1] 张海娜[1] 马玉芳[1] 

机构地区：[1]商丘工学院,河南商丘476000

出　　处：《激光杂志》2017年第2期94-97,共4页Laser Journal

基　　金：河南省科技攻关课题(162102210361)

摘　　要：针对当前激光雷达图像识别精度低的难题,提出了基于向量机的激光雷达图像识别方法。首先对激光雷达图像进行预处理,重构模糊视觉特征,提取显著像素点特征,然后以激光雷达图像的显著像素点特征作为分类器输入数据,利用模式识别算法—支持向量机分类器进行模式识别,实现对激光雷达图像的特征分类和准确识别,最后实验结果表明,该方法的激光雷达图像分类识别准确度高于传统方法。In view of the current laser radar image recognition accuracy is not high question, put forward a kind of pattern recognition based on support vector machine classification analysis of the laser radar image recognition method, the acquisition of laser radar image reconstruct blurred vision characteristics, extract the significant characteristics of pixels, to extract the laser radar image pixels feature as a classifier input data, using support vector machine classifier to pattern recognition, implementation of the characteristics of the laser radar image classification and accurate recognition. Experimental analysis results show that by using this method for laser radar image classification accuracy is higher than the traditional method.

关 键 词：模式识别 激光雷达图像 识别准确度 支持向量机 

分 类 号：TN919.8[电子电信—通信与信息系统]