摘要
在绿化结构信息提取中由于采集到的图像中存在大量斑点噪声,影响信息提取完整度,为此提出基于三维GIS的城市道路绿化结构信息提取方法。在三维地理信息系统(GIS)的支持下采用激光扫描技术获取城市道路图像;将贝叶斯原理引入小波分解过程中,通过对数变化消除城市道路图像中存在的斑点噪声;采用模糊C均值聚类方法聚类处理去噪后的城市道路图像,提取绿化像素点,通过细化聚类结果建立Snakes模型,提取城市道路绿化结构信息。仿真结果表明,所提方法可有效消除斑点噪声、信息提取完整度高、提取精度高。
At present,a large amount of speckle noise in the collected images affects the completeness of informa-tion extraction.Therefore,a method of extracting greening structure information of urban roads was proposed based on 3D GIS.Under the support of three-dimensional geographic information system(GIS),laser scanning technology was used to collect the images of urban roads.The Bayesian principle was also introduced into the wavelet decomposition process.And then,logarithmic change was used to eliminate the speckle noise in images.Moreover,the fuzzy C-means clustering method was adopted to cluster the denoised images,thus extracting green pixels.Finally,a Snakes model was built by refining the clustering results.Thus,the greening structure information of urban roads was extrac-ted.Simulation results prove that the proposed method can effectively eliminate speckle noise and improve the integrity and accuracy of information extraction.
作者
全震
吕静
QUAN Zhen;LV Jing(School of Architecture&Design,Changchun Instituteof Technology,Changchun Jilin 130000,China;School of Architecture and Planning Jilin Jianzhu University,Changchun Jilin 130000,China)
出处
《计算机仿真》
北大核心
2023年第6期216-219,337,共5页
Computer Simulation
关键词
城市道路绿化结构
信息提取
仿真
3D GIS
Greening structure of urban roads
Fuzzy C-means clustering
Snakes model
Information extraction
