This paper presents a novel algorithm for detecting pavement cracks from mobile laser scanning (MLS) data. The algorithm losslessly transforms MLS data into a regular grid structure to adopt the proven image-based methods of crack extraction. To address the problem of lacking topology, this study assigns a two-dimensional index for each laser point depending on its scanning angle or acquisition time. Next, crack candidates are identified by integrating the differential intensity and height changes from their neighbors. Then, morphology filtering, a thinning algorithm, and the Freeman codes serve for the extraction of the edge and skeleton of the crack curves. Further than the other studies, this work quantitatively evaluates crack shape parameters: crack direction, width, length, and area, from the extracted crack points. The F1 scores of the quantity of the transverse, longitudinal, and oblique cracks correctly extracted from the test data reached 96.55%, 87.09%, and 81.48%, respectively. In addition, the average accuracy of the crack width and length exceeded 0.812 and 0.897. Experimental results demonstrate that the proposed approach is robust for detecting pavement cracks in a complex road surface status. The proposed method is also promising in serving the extraction of other on-road objects.

Trajectory data are often used as important auxiliary information in preprocessing and extracting the target from mobile laser scanning data. However, the trajectory data stored independently may be lost and destroyed for various reasons, making the data unavailable for the relevant models. This study proposes recovering the trajectory of the scanner from point cloud data following the scanning principles of a rotating mirror. Two approaches are proposed from different input conditions: Ordered three-dimensional coordinates of point cloud data, with and without acquisition time. We recovered the scanner’s ground track through road point density analysis and restored the position of the center of emission of the laser based on plane reconstruction on a single scanning line. The validity and reliability of the proposed approaches were verified in the four typical urban, rural, winding, and viaduct road environments using two systems from different manufacturers. The result deviations of the ground track and scanner trajectory from their actual position were a few centimeters and less than 1 decimeter, respectively. Such an error is sufficiently small for the trajectory data to be used in the relevant algorithms.

Various means of extracting road boundary from mobile laser scanning data based on vehicle trajectories have been investigated. Independent of positioning and navigation data, this study estimated the scanner ground track from the spatial distribution of the point cloud as an indicator of road location. We defined a typical edge block consisting of multiple continuous upward fluctuating points by abrupt changes in elevation, upward slope, and road horizontal slope. Subsequently, such edge blocks were searched for on both sides of the estimated track. A pseudo-mileage spacing map was constructed to reflect the variation in spacing between the track and edge blocks over distance, within which road boundary points were detected using a simple linear tracking model. Experimental results demonstrate that the ground trajectory of the extracted scanner forms a smooth and continuous string just on the road; this can serve as the basis for defining edge block and road boundary tracking algorithms. The defined edge block has been experimentally verified as highly accurate and strongly noise resistant, while the boundary tracking algorithm is simple, fast, and independent of the road boundary model used. The correct detection rate of the road boundary in two experimental data is more than 99.2%.

In this paper, the new method is proposed for filtering of airborne LiDAR data based on improved Triangulated Irregular Network(TIN) algorithm and the details of filter principle is described. Firstly, LiDAR point cloud data is organized and designed by regular grid and TIN, the seed points from point cloud data are selected by regional sub-block method or mathematical morphology. Then, an initial sparse TIN is created from the seed points and densified upward gradually and the ground points are extracted through an interactive process. In experiments it is shown that this filtering method can effectively remove different sizes of buildings, low vegetation and other objects, and keep topographical features better.

In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.