Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds

Abstract

Mobile Laser Scanning (MLS) point cloud data contains rich three-dimensional (3D) information on road ancillary facilities such as street lamps, traffic signs and utility poles. Automatically recognizing such information from point cloud would provide benefits for road safety inspection, ancillary facilities management and so on, and can also provide basic information support for the construction of an information city. This paper presents a method for extracting and classifying pole-like objects (PLOs) from unstructured MLS point cloud data. Firstly, point cloud is preprocessed to remove outliers, downsample and filter ground points. Then, the PLOs are extracted from the point cloud by spatial independence analysis and cylindrical or linear feature detection. Finally, the PLOs are automatically classified by 3D shape matching. The method was tested based on two point clouds with different road environments. The completeness, correctness and overall accuracy were 92.7%, 97.4% and 92.3% respectively in Data I. For Data II, that provided by International Society for Photogrammetry and Remote Sensing Working Group (ISPRS WG) III/5 was also used to test the performance of the method, and the completeness, correctness and overall accuracy were 90.5%, 97.1% and 91.3%, respectively. Experimental results illustrate that the proposed method can effectively extract and classify PLOs accurately and effectively, which also shows great potential for further applications of MLS point cloud data.

Pole-Like Street Furniture Segmentation and Classification in Mobile LiDAR Data by Integrating Multiple Shape-Descriptor Constraints

“…For pole-like street furniture segmentation, most state-of-the-art methods perform isolation analysis [1,17,18], detect geometric linear features based on confusion matrices [19][20][21], accurately model pole-like street furniture by RANSAC algorithm [10,11] and conduct voxel or supervoxel-based segmentation [1,15,20,[22][23][24][25][26][27][28][29]. Brenner et al first proposed a double-cylinder model to perform isolation analysis, in which the pole-part should be surrounded by an inner cylinder and there should be no points in between the inner and outer cylinders [17].…”

“…They detect pole-like street furniture by identifying the linear structures using a 2D density-based method, a slice cutting-based method and a RANSAC (Random sample consensus) model fitting method [10,11]. Other state-of-art methods concentrate on segmenting pole-like street furniture by reorganizing the original point clouds to voxels [1,22,23,25,26] or supervoxels [15,20,24,[27][28][29]. Cabo et al introduced the voxelization method for pole-like street furniture extraction [1,22].…”

“…They found a pole part by two-dimensional (2D) analysis based on the horizontal section of the voxels, then they clustered and segmented pole-like street furniture based on voxel connectivity analysis. Shi et al removed outliers from the original point clouds and voxelized the rest of the point clouds for the first time to down-sample the data [23]. After ground removal, they voxelized the remaining point clouds for the second time for further pole-like furniture segmentation.…”

“…The object locations are identified first and then the connected objects are separated by using the 3D object density variations. Yu and Glowinski utilized the graph-cut method from computer vision to separate connected and overlapped objects [21][22][23]. With a given object location, a k-nearest neighbor graph was built, and then the connected objects were separated based on energy minimization.…”

High-Resolution Representation for Mobile Mapping Data in Curved Regular Grid Model

“…These systems produce large-scale 3D point clouds and very-high-precision geometric measurements. The produced point clouds are used for many road-related research tasks, including missing road point regions detection [13], road damage information detection [14,15], road segmentation and recognition [16,17], etc.…”