近景图像序列线特征约束的建筑物立面重建

Building facade modeling under line feature constraint based on close-range images

针对单纯利用近景图像序列点特征进行建筑物立面重建存在的问题,该文提出一种线特征约束下建筑物建模方法。首先利用运动恢复结构技术恢复相机参数和空间点云数据,并在此基础上利用多视图立体方法生成三维稠密点云;然后对图像序列进行基于梯度方向的边缘检测及顾及方向和长度的直线特征拟合;再利用多约束条件实现直线特征匹配及提取;最后基于三维点、线特征实现建筑物立面的三维重建。实验结果表明,该方法能有效利用近景图像序列点、线特征的优势互补重建建筑物的几何立面,更好地恢复建筑物立面的轮廓信息。

To solve problems in modeling facade of building with point feature based on close-range images,a new modeling method for building facade under line feature constraint was proposed in this paper.Firstly,camera parameters and sparse spatial point clouds data were restored using the SFM method,and 3 Ddense point clouds were generated with MVS;secondly,the line features were detected based on the gradient direction,those detected line features were fit considering the directions and lengths,then line features were matched under multiple types of constraints and extracted from multi-image sequence.At last,final facade of a building was modeled with point cloud and line features.The experiment showed that this method could effectively reconstruct the geometric facade of buildings using the advantages of combining point and line features of the close-range image sequence,thus obtain better results in restoring the contour information of the facade of buildings.