摘要
传统建筑物顶面损毁区域检测方法存在图像灰度级不理想、信息提取准确度低的问题。为此,提出新的基于三维点云的建筑物顶面损毁区域信息提取方法。分析建筑物损毁区域顶面特征结构分布图,获得可靠聚类种子点,构建邻域投票模型,使建筑物损毁区域顶面图像的错分现象降到最低。结合RANASC方法构建主动提炼准则平面模型,实现建筑顶面损毁区域图像信息的提取。为验证研究的有效性,进行一次仿真。实验结果证明:研究方法获取的图像灰度级更优,有效提高了图像清晰度,能更准确提取建筑物顶面损毁区域信息。
Traditional detection methods lead to some problems,such as low accuracy and poor gray level.Therefore,a method to extract the information of damaged area on the top of buildings based on 3 D point cloud was proposed.By analyzing the distribution map of feature structure,we got reliable clustering seed points,and constructed neighborhood voting model to minimize the misclassification of the image of damaged area on the top of buildings.Combined with RANASC method,we built the active extraction criterion plane model to extract the image information of the damaged area on the top of buildings.In order to verify the effectiveness of research,a simulation experiment was carried out.Simulation results show that the gray level of image obtained by the proposed method is better,and the image clarity is improved effectively,so that the information of the damaged area on the top of buildings can be extracted more accurately.
作者
赵伟卓
ZHAO Wei-zhuo(College of Applied Science,Jiangxi University of Science and Techonology,Ganzhou Jiangxi 341000,China)
出处
《计算机仿真》
北大核心
2020年第6期462-465,共4页
Computer Simulation
基金
江西省教育厅科学技术研究项目(GJJ171502)。
关键词
三维点云
建筑物
损毁区域
信息提取
3D point cloud
Building
Damaged area
Information extraction
