Pavement Crack Detection from Mobile Laser Scanning Point Clouds Using a Time Grid

Abstract

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.

Deep Learning-Based Thermal Image Analysis for Pavement Defect Detection and Classification Considering Complex Pavement Conditions

“…Data Type Accuracy (%) Zhang et al [47] RGB image (Kinect-Based) 89.09 Zhou and Song [22] laser-scanned range images 99.6 (average) Zhong et al [9] 3D laser scanning Over 98 Chen et.al. [6] vibration signal 97.2 Our method RGB image with thermal information 98.34%…”

“…However, for the actual complex road conditions, the existing methods have limited error detection rates to identify all kinds of cases [5]. Multi-sensor fusion processing idea for complex road conditions was considered where acceleration sensors [6], infrared sensors [7], multi-vision cameras [8], and 3D laser scanning [9] can provide additional identification information to the optical images of the pavement.…”

PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network

“…In [12], [14], the point clouds of concrete surfaces are projected to a 2D plane producing range images and are used for detection, for example, applying DNN method on the images [17]. Other methods include grid search [10] and plane fitting [15] which have been applied on pavement and timber point clouds, respectively. Defects on aeroplane exteriors have been detected using region growing on the surface normal estimation [16].…”

“…These vision-based methods have shown promising results, but have been seen to struggle when applied to more challenging environments where the surface is unstructured [5]. 3D sensors have also been utilised for crack and defects detection, however, they have been applied on similar structural domains such as pavements [10], [11], concrete [12], [13], [14], timber [15] and aeroplane exterior [16].…”

An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm

“…However, crack points account for only a small proportion of mobile laser scanning data, which made Otsu’s threshold unreliable for segmented cracks. According to the scanning angle and time of the scanner, Zhong et al [ 29 ] established a 2D index for each point cloud to reduce the dimensionality in a non-destructive manner, and reflectance and depth information were then used to extract cracks. Since the density of a 3D point cloud is not high enough, existing 3D methods often make it difficult to detect small cracks.…”