The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection on 3D asphalt surfaces with explicit objective of pixel-perfect accuracy. Unlike the commonly used CNN, CrackNet does not have any pooling layers which downsize the outputs of previous layers. CrackNet fundamentally ensures pixel-perfect accuracy using the newly developed technique of invariant image width and height through all layers. CrackNet consists of five layers and includes more than one million parameters that are trained in the learning process. The input data of the CrackNet are feature maps generated by the feature extractor using the proposed line filters with various orientations, widths, and lengths. The output of CrackNet is the set of predicted class scores for all pixels. The hidden layers of CrackNet are convolutional layers and fully connected layers. CrackNet is trained with 1,800 3D pavement images and is then demonstrated to be successful in detecting cracks under various conditions using another set of 200 3D pavement images. The experiment using the 200 testing 3D images showed that CrackNet can achieve high Precision (90.13%), Recall (87.63%) and F-measure (88.86%) simultaneously. Compared with recently developed crack detection methods based on traditional machine learning and imaging algorithms, the CrackNet significantly outperforms the traditional approaches in terms of F-measure. Using parallel computing techniques, CrackNet is programmed to be efficiently used in conjunction with the data collection software.

A recurrent neural network (RNN) called CrackNet‐R is proposed in the article for fully automated pixel‐level crack detection on three‐dimensional (3D) asphalt pavement surfaces. In the article, a new recurrent unit, gated recurrent multilayer perceptron (GRMLP), is proposed to recursively update the internal memory of CrackNet‐R. Unlike the widely used long short‐term memory (LSTM) and gated recurrent unit (GRU), GRMLP is intended for deeper abstractions on the inputs and hidden states by conducting multilayer nonlinear transforms at gating units. CrackNet‐R implements a two‐phase sequence processing: sequence generation and sequence modeling. Sequence generation is specifically developed in the study to find the best local paths that are most likely to form crack patterns. Sequence modeling predicts timely probabilities of the input sequence being a crack pattern. In terms of sequence modeling, GRMLP slightly outperforms LSTM and GRU by using only one more nonlinear layer at each gate. In addition to sequence processing, an output layer is proposed to produce pixel probabilities based on timely probabilities predicted for sequences. The proposed output layer is critical for pixel‐perfect accuracy, as it accomplishes the transition from sequence‐level learning to pixel‐level learning. Using 3,000 diverse 3D images, the training of CrackNet‐R is completed through optimizing sequence modeling, sequence generation, and the output layer serially. The experiment using 500 testing pavement images shows that CrackNet‐R can achieve high Precision (88.89%), Recall (95.00%), and F‐measure (91.84%) simultaneously. Compared with the original CrackNet, CrackNet‐R is about four times faster and introduces tangible improvements in detection accuracy.

Accurate identification of cracks at the pixel level on intricate asphalt pavements represents a crucial challenge in the domain of intelligent pavement assessment. The current advanced deep-learning networks encounter limitations in simultaneously capturing both the global context and local features of cracks, leading to discontinuous segmentation results and suboptimal recovery of local details. This paper proposes a robust architecture named Mix-Graph CrackNet to present an efficacious solution for this challenge. The Mix-Graph CrackNet, as proposed, is designed to mix the global context and local features multiple times, allowing for a comprehensively understanding of the essential features. Specifically, this paper develops the learnable parallel convolutional-Transformer mixing module to parallelly capture the sophisticated local features as well as the crucial global context. In addition, a new fusion unit is devised in the paper and deployed in the learnable parallel convolutional-Transformer mixing module. The proposed fusion unit is capable of effectively mixing contextual features extracted at both global and local scales while retaining an abundant level of textural details germane to the crack. Moreover, this paper constructs a graph-based skip connection that functions as a shortcut connecting the encoder and decoder, with the primary objective of mitigating information decay. The experimental results are remarkable, with the Mix-Graph CrackNet achieving F-measure and Intersection-Over-Union of 90.37% and 82.43%, respectively, on 1000 testing images. Based on the performance evaluations conducted on both public and private datasets, the proposed Mix-Graph CrackNet architecture demonstrates a significantly superior detection accuracy in comparison to several state-of-the-art models for semantic segmentation.

Skid resistance is an important surface characteristic that influences roadway safety. Various studies have been performed to understand the interaction between pavement and tires through numerical simulation for skid resistance prediction. However, the friction parameters required for simulation inputs are generally determined by objective assumptions. This paper develops a finite element method (FEM)-based skid resistance simulation framework using in-situ 3D pavement surface texture and skid resistance data. A 3D areal pavement model is reconstructed from high resolution asphalt pavement surface texture data. The exponential decay friction model is implemented in the simulation and the interface friction parameters required for the simulation are determined using the binary search back-calculation approach based on a trial process with the desired level of differences between simulated and observed skid numbers. To understand the influence of texture characteristics on interface friction parameters, the high-resolution 3D texture data is separated into macro- and micro-scales through Butterworth filtering and various areal texture indicators are calculated at both levels. Principal component analysis (PCA) regression analysis is conducted to quantify the relationship between various texture characteristics and the interface friction parameters. The results from this study can be used to better prepare the inputs of friction parameters for FEM simulation.

A bstract: Lane marking detection and localization are crucial for autonomous driving and lane-based pavement surveys. Numerous studies have been done to detect and locate lane markings with the purpose of advanced driver assistance systems, in which image data are usually captured by vision-based cameras. However, a limited number of studies have been done to identify lane markings using high-resolution laser images for road condition evaluation. In this study, the laser images are acquired with a digital highway data vehicle (DHDV). Subsequently, a novel methodology is presented for the automated lane marking identification and reconstruction, and is implemented in four phases: (1) binarization of the laser images with a new threshold method (multi-box segmentation based threshold method); (2) determination of candidate lane markings with closing operations and a marching square algorithm; (3) identification of true lane marking by eliminating false positives (FPs) using a linear support vector machine method; and (4) reconstruction of the damaged and dash lane marking segments to form a continuous lane marking based on the geometry features such as adjacent lane marking location and lane width. Finally, a case study is given to validate effects of the novel methodology. The findings indicate the new strategy is robust in image binarization and lane marking localization. This study would be beneficial in road lane-based pavement condition evaluation such as lane-based rutting measurement and crack classification.

The paper proposes an interactive algorithm for a three-dimensional (3D) surface that can substantially improve its cracking detection performance by adjustments based on the observer’s feedback. Since the correct response to the observer’s feedback is critical to the performance of an interactive algorithm, the paper presents a series of novel methodologies to accomplish the interaction between the detection system and the observer with a high level of success. A computer program is developed to establish the interactive detection system and implement two levels of detection. The bottom level is automated and can be used to find the majority of cracking. The top level is assisted by the users and can be applied for semi-automated refinement. In particular, the top level is designated to find missed cracks or delete noises within user-defined regions. The techniques of precision recall and confusion matrix are used to determine effectiveness of the developed system of algorithms. The results from ...