面向阵列InSAR点云规则化的渐近式建筑立面检测

为有效地从海量、带噪阵列 InSAR 空间点中检测建筑立面，本文提出一种基于结构先验的渐进式 建筑立面检测算法。本文算法首先将初始阵列 InSAR 空间点投影至地面以生成与建筑立面相应的连通区 域，然后通过结构先验的引导逐步在每个连通区域内检测潜在的线段，进而根据线段及其对应的空间点 生成相应的建筑立面；在此过程中，当前连通区域对应线段的检测空间根据其相邻连通区域内已检测线 段构造，有效保证了整体效率与可靠性。实验结果表明，本文算法可快速从海量、带噪阵列 InSAR 空间 点中检测出较多的可靠建筑立面，较好地克服了传统多模型拟合算法效率低与可靠性差的缺点。To effectively detect building facades from massive, noisy array InSAR spatial points, this paper proposes a progressive building facade detection algorithm based on structural priors. The proposed algorithm first projects the initial array InSAR spatial points onto the ground to generate connected regions corresponding to building facades, then gradually detects potential line segments within each connected region under the guidance of structural priors, and further generates corresponding building facades based on the line segments and their corresponding spatial points. During this process, the detection space for line segments corresponding to the current connected region is constructed based on the detected line segments in its adjacent connected regions, which effectively guarantees the overall efficiency and reliability. Experimental results demonstrate that the proposed algorithm can quickly detect a considerable number of reliable building facades from massive, noisy array InSAR spatial points, and well overcomes the drawbacks of low efficiency and poor reliability of traditional multi-model fitting algorithms.

搜集汇总

背景与挑战

背景概述

该数据集提供了一种渐近式建筑立面检测方法，用于从带噪声的阵列InSAR点云中高效提取建筑立面。该方法基于结构先验，通过投影3D点、检测线段并利用相邻区域信息，克服了传统方法在效率和可靠性方面的不足。数据集包含相关算法实现或数据，适用于遥感、建筑检测和点云处理领域的研究。