徐文学, 杨必胜, 董震, 彭向阳, 麦晓明, 王珂, 高文武. 标记点过程用于点云建筑物提取[J]. 武汉大学学报 ( 信息科学版), 2014, 39(5): 520-525. DOI: 10.13203/j.whugis20130044
引用本文: 徐文学, 杨必胜, 董震, 彭向阳, 麦晓明, 王珂, 高文武. 标记点过程用于点云建筑物提取[J]. 武汉大学学报 ( 信息科学版), 2014, 39(5): 520-525. DOI: 10.13203/j.whugis20130044
XU Wenxue, YANG Bisheng, DONG Zhen, PENG Xiangyang, MAI Xiaoming, WANG Ke, GAO Wenwu. Building Extraction from Point Cloud Using Marked Point Process[J]. Geomatics and Information Science of Wuhan University, 2014, 39(5): 520-525. DOI: 10.13203/j.whugis20130044
Citation: XU Wenxue, YANG Bisheng, DONG Zhen, PENG Xiangyang, MAI Xiaoming, WANG Ke, GAO Wenwu. Building Extraction from Point Cloud Using Marked Point Process[J]. Geomatics and Information Science of Wuhan University, 2014, 39(5): 520-525. DOI: 10.13203/j.whugis20130044

标记点过程用于点云建筑物提取

Building Extraction from Point Cloud Using Marked Point Process

  • 摘要: 目的 提出了利用标记点过程从机载激光扫描数据中直接提取建筑物的方法。该方法首先根据建筑物在点云中的几何特征建立Gibbs能量模型,通过目标的一致性建立模型的数据项,通过目标的拓扑性质等空间特性建立模型的先验项;然后,利用可逆跳转马尔科夫蒙特卡洛算法(RJMCMC)和模拟退火算法优化求解;最后,利用精细处理移除错误提取的地面点、噪声点和树木点,合并相邻的目标,实现建筑物目标的精确提取。利用3组ISPRS机载激光扫描点云进行实验,结果表明,该方法能够准确、有效地提取建筑物,具有较强的稳健性。

     

    Abstract: Objective In this paper,a marked point process based method is used to extract buildings from air-borne LIDAR data.At first,a Gibbs energy model is build according to the geometric feature of theobject in the point cloud data.This model contains both a data coherence term which fits the objects tothe data and a prior term which incorporates the prior knowledge of the object geometric properties.Then the previously defined model is optimized by the RJMCMC(Reverse Jump Markov Chain MonteCarlo)algorithm and simulated annealing algorithm.Finally,fine processing removes the terrestrialpoints,noise points and tree crown points of the extracted objects which are mistakenly extracted asbuildings,while combining adjacent objects.The method was tested with three different aerial LiDARdata sets from ISPRS.The results show that our method is capable of efficient and robust building ex-traction.

     

/

返回文章
返回