Pavement Crack Detection and Clustering via Region-Growing Algorithm from 3D MLS Point Clouds

Abstract

Road condition monitoring plays a critical role in transportation infrastructure maintenance and traffic safety assurance. This research introduces a methodology to detect cracks on pavement point clouds acquired with Mobile Laser Scanning systems, which offer more versatility and comprehensive information about the road environment than other specific surveying systems (i.e., profilometers, 3D cameras). The methodology comprises the following steps: (1) Road segmentation; (2) the detection of candidate crack points in individual scanning lines of the point cloud, based on point elevation; (3) crack point clustering via a region-growing algorithm; and (4) crack geometrical attributes extraction. Both the profile evaluation and the region-growing clustering algorithms have been developed from scratch to detect cracks directly from 3D point clouds instead of using raster data or Geo-Referenced Feature images, offering a quick and effective pre-rating tool for pavement condition assessment. Crack detection is validated with data from damaged roads in Portugal.

Civil Integrated Management (CIM) for Advanced Level Applications to Transportation Infrastructure: A State-of-the-Art Review

“…It is worth mentioning that innovative approaches such as video processing, laser scanners, and point cloud data were also utilized to detect, generate, and evaluate 3D information models of the terrain condition [53,87] and roadway elements [33,40,58,88,89]. A new method utilizing a mobile laser scanner (MLS) has been presented as providing more information including road segmentation, potential crack point detection based on point elevation, crack point clustering using a region-growing algorithm, and extraction of crack geometric attributes [34]. The vertical and horizontal clearances of highway viaducts and gantries can be automatically estimated using MLS point clouds for routing oversized transport items, infrastructure reconstruction, maintenance, and settling legal claims after incidents [90].…”

Segmentation method of drivable areas of mine roads based on rut texture features

“…In order to improve the accuracy of the segmented region, the post-processing is carried out. Based on the difference of the gray value inside and outside the hole, the region growing algorithm [13] is used to detect the boundary pixel points by using the 8 neighborhood, the convolution operation is carried out by using the morphological method to fill the hole. The filling of the holes is achieved by equation (7):…”

A panoramic driving perception fusion algorithm based on multi-task learning

“…In autonomous driving, the car driving system needs to understand the complex road environment in which the vehicle is located, including elements such as lane lines, traffic signs, and pedestrians. In order to achieve a more comprehensive and accurate understanding of the driving environment, key scene elements are identified and extracted through the region growing clustering algorithm [ 35 ], and obstacles are segmented based on the local information and features of the point cloud, clustering adjacent points together to form accurate obstacle boundaries, thereby achieving more reliable obstacle perception and tracking. The region growing clustering algorithm can adaptively determine the parameters of clustering, such as the minimum or maximum clustering range, the number of neighborhood points.…”