Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov 25;22(23):9183.
doi: 10.3390/s22239183.

Pavement Distress Estimation via Signal on Graph Processing

Salvatore Bruno  1 , Stefania Colonnese  2 , Gaetano Scarano  2 , Giulia Del Serrone  1 , Giuseppe Loprencipe  1
Affiliations

Pavement Distress Estimation via Signal on Graph Processing

Salvatore Bruno et al. Sensors (Basel). .

Abstract

A comprehensive representation of the road pavement state of health is of great interest. In recent years, automated data collection and processing technology has been used for pavement inspection. In this paper, a new signal on graph (SoG) model of road pavement distresses is presented with the aim of improving automatic pavement distress detection systems. A novel nonlinear Bayesian estimator in recovering distress metrics is also derived. The performance of the methodology was evaluated on a large dataset of pavement distress values collected in field tests conducted in Kazakhstan. The application of the proposed methodology is effective in recovering acquisition errors, improving road failure detection. Moreover, the output of the Bayesian estimator can be used to identify sections where the measurement acquired by the 3D laser technology is unreliable. Therefore, the presented model could be used to schedule road section maintenance in a better way.

Keywords: Bayesian estimator; automated distress evaluation systems; pavement condition index; pavement distress detection; pavement management program; signal on graph processing.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
A modern data collection vehicle.
Figure 2
Figure 2
LCMS sensors installed on the surveying vehicle.
Figure 3
Figure 3
Pavement distress detected (severity = color code).
Figure 4
Figure 4
Framework for the pavement distress estimation via SoG processing.
Figure 5
Figure 5
Standard PCI rating scale.
Figure 6
Figure 6
Distress road model as a signal on graph.
Figure 7
Figure 7
Product of graphs example for the toy case considering P = 5 metrics (P1, P2, P3, P4, P5) measured at M = 4 sections (M1, M2, M3, M4): (a) graph of the metrics’ correlation at a given section); (b) path graph representing the similarity of the same metric over adjacent spatial sections; (c) overall product graph.
Figure 8
Figure 8
Effect of the nonlinear estimator on the observed value as the p0 (a) and the β0 parameter (b) change; the case of observed value equal to 6.2 is highlighted.
Figure 9
Figure 9
P = 5 metrics, M = 4 sections graph schematically represented in Figure 6. MSE of the Bayesian estimator (Bay), the linear estimate obtained averaging over neighboring graph vertices (Graph), the linear estimate obtained averaging over spatially adjacent vertices (Mean) and the nonlinear estimate obtained as the median over spatially adjacent vertices (Median).
Figure 10
Figure 10
Examined roads—2468 km.
Figure 11
Figure 11
Adjacency matrix coefficients aij(1) i,j=0, …P−1 of the graph of the metrics, calculated as the correlation coefficients between the i-th and j-th distress metric values: (a) original values and (b) thresholded values with threshold ϑ=0.1.
Figure 12
Figure 12
Correlations between the different investigated metrics.
Figure 13
Figure 13
Measurements involved in the estimation of the i-th metric at the n-th inspected section (black square): measurements relative to correlated metrics at the same inspected section (light blue squares), and measurements of the same metric averaged over spatially adjacent sections (yellow squares).
Figure 14
Figure 14
The maximum measured values for each of the metrics.
Figure 15
Figure 15
Metrics normalized to the maximum measured values.
Figure 16
Figure 16
Test Set. MSE of the Bayesian estimator (Bay), the linear estimate obtained averaging over neighboring graph vertices (Graph), the linear estimate obtained averaging over spatially adjacent vertices (Mean) and the nonlinear estimate obtained as the median over spatially adjacent vertices (Median).
Figure 17
Figure 17
The measured values (blue) and the estimated values with nonlinearity (orange) for each of the metrics.
Figure 18
Figure 18
The difference between the measured values and the estimated values with non-linearity.
Figure 19
Figure 19
PCI correction due to Bayesian estimator in terms of relative frequency (a) and cumulative frequency (b).
See this image and copyright information in PMC

References

    1. Cafiso S., Di Graziano A., Goulias D.G., D’Agostino C. Distress and Profile Data Analysis for Condition Assessment in Pavement Management Systems. Int. J. Pavement Res. Technol. 2019;12:527–536. doi: 10.1007/s42947-019-0063-7. - DOI
    1. Queiroz C.A., Gautam S. Road Infrastructure and Economic Development: Some Diagnostic Indicators. Volume 921 World Bank Publications; Washington, DC, USA: 1992.
    1. Ragnoli A., De Blasiis M., Di Benedetto A. Pavement Distress Detection Methods: A Review. Infrastructures. 2018;3:58. doi: 10.3390/infrastructures3040058. - DOI
    1. Bruno S., Vita L., Loprencipe G. Development of a GIS-Based Methodology for the Management of Stone Pavements Using Low-Cost Sensors. Sensors. 2022;22:6560. doi: 10.3390/s22176560. - DOI - PMC - PubMed
    1. Hafizyar R., Mosaberpanah M. Evaluation of Flexible Road Pavement Condition Index and Life Cycle Cost Analysis of Pavement Maintenance: A Case Study in Kabul Afghanistan. Int. J. Sci. Eng. Res. 2018;9:1909.

LinkOut - more resources