Linear feature extraction from point cloud using color information

Abstract

LiDAR is considered as an effective technology for digitizing the real scene at a very high-resolution and in a short time. However, the resolution of the LiDAR is not sufficient to identify and evaluate the façade surface features like edges and cracks. Generally, photographs provide a better interpretation of the linear characteristics. The complementary benefits of each allow exploring valuable spatial information with different surface detail levels. The paper introduces a flexible image-based approach for linear feature extraction from LiDAR point cloud. Initially, the algorithm converts the point clouds into a structured depth image to reduce the complexity and computation time. Using transformation matrix and camera calibration parameters, the visible point clouds are perceptively projected into color image space using co-linearity equations. The result depth channel is sampled with the interpolation process and added to the color channels to compute (RGBD) layers. The edges and linear features of the surface are initially extracted using the optical 2D imagery and subsequently, each pixel of the linear features can be projected directly into 3D space. Due to the various acquisition positions of the laser and color images, the issue of occlusion is resolved using the visibility algorithm. Applying the methodology, experimental results from the Treasury Monument of Jordan’s ancient Petra City, indicate that the developed approach provides adequate contour points for better interpretation and quantification of weathering processes and dangerous cracking. 3D Modeling these features can also reduce data size, facilitating surface inspection and analysis with simpler models.