基于投影点密度的车载激光扫描距离图像分割方法

Abstract

对车载激光扫描系统获取的距离图像的分割进行研究,提出利用投影点密度进行距离图像分割的方法。该方法不需要其他辅助数据就可以进行距离图像的分割,给出应用实例。图像的分割是目标识别、定位、特征提取与建模的基础和关键。距离图像是离散坐标点阵列,不表达目标边界特征和拓扑关系,到目前为止还没有距离图像分割的成熟、可行方法。本文研究成果,展现了激光扫描技术在数据获取、处理研究上的新方向。 The research presented in this paper is focused on segmentation of range image captured by vehicle-borne laser scanning systems. A method, named as Density of Projected Points (DoPP) is proposed for the range image segmentation without other auxiliary data and is conducted to demonstrate the feasibility of the proposed solution by two cases. Image segmentation is the foundation and crux of object recognization, positioning, feature extraction and modeling. Range image is the discrete array of coordinates, which cannot describe edge feature or topologic relation, it has not be segmented by mature and feasible methods of segmentation up to now. The investigation in this paper opens a research direction to data acquisition and processing of laserscanning.