融合激光扫描强度和遥感信息的建筑物分类研究

Building Classification Based on Laser Scanning Intensity and Remote Sensing Message

针对当前建筑物分类技术存在的难题,以提高建筑物分类的正确率为目标,提出一种融合激光扫描强度信息和遥感信息的建筑物分类方法。首先分析了当前建筑物分类技术的研究现状,并利用激光扫描强度信息进行建筑物分类第一次类,最后根据遥感图像信息获取采用支持向量机对建筑物进行第二次分类,并采用具体建筑物分类应用实例进行测试和分析。结果表明,本文方法的建筑物分类正确率高达96%以上,可以准确描述建筑物的类别信息,分类结果要明显优于当前经典建筑物分类方法,具有广泛的应用前景。

In order to solve the problems existing in the current building classification technology and improve the accuracy of building classification, a building classification model based on laser scanning intensity information and femote sensing information is proposed in this paper. Firstly, analyzes research status of current building classification technology, and secondly, the laser scanning intensity information is used to classity buildings for the first time, finally, the support vector machine is used to obtain buildings classification model of based on remote sensing image information and the performances are tested and analyzed with specific building classification data. The results show that building classification accuracy of the proposed model is more than 96%, buildings. The classification results are significantly better than that and has a wide application prospect.