Pothole properties measurement through visual 2D recognition and 3D reconstruction

G. M. Jog, C. Koch, M. Golparvar-Fard, I. Brilakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Current pavement condition assessment methods are predominantly manual and time consuming. Existing pothole recognition and assessment methods rely on 3D surface reconstruction that requires high equipment and computational costs or relies on acceleration data which provides preliminary results. This paper presents an inexpensive solution that automatically detects and assesses the severity of potholes using vision-based data for both 2D recognition and for 3D reconstruction. The combination of these two techniques is used to improve recognition results by using visual and spatial characteristics of potholes and measure properties (width, number, and depth) that are used to assess severity of potholes. The number of potholes is deduced with 2D recognition whereas the width and depth of the potholes is obtained with 3D reconstruction. The proposed method is validated on several actual potholes. The results show that the proposed inexpensive and visual method holds promise to improve automated pothole detection and severity assessment.

Original languageEnglish (US)
Title of host publicationComputing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering
Pages553-560
Number of pages8
DOIs
StatePublished - Dec 1 2012
Externally publishedYes
Event2012 ASCE International Conference on Computing in Civil Engineering - Clearwater Beach, FL, United States
Duration: Jun 17 2012Jun 20 2012

Publication series

NameCongress on Computing in Civil Engineering, Proceedings

Other

Other2012 ASCE International Conference on Computing in Civil Engineering
CountryUnited States
CityClearwater Beach, FL
Period6/17/126/20/12

Fingerprint

Surface reconstruction
Pavements
Costs

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Computer Science Applications

Cite this

Jog, G. M., Koch, C., Golparvar-Fard, M., & Brilakis, I. (2012). Pothole properties measurement through visual 2D recognition and 3D reconstruction. In Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering (pp. 553-560). (Congress on Computing in Civil Engineering, Proceedings). https://doi.org/10.1061/9780784412343.0070

Pothole properties measurement through visual 2D recognition and 3D reconstruction. / Jog, G. M.; Koch, C.; Golparvar-Fard, M.; Brilakis, I.

Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering. 2012. p. 553-560 (Congress on Computing in Civil Engineering, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jog, GM, Koch, C, Golparvar-Fard, M & Brilakis, I 2012, Pothole properties measurement through visual 2D recognition and 3D reconstruction. in Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering. Congress on Computing in Civil Engineering, Proceedings, pp. 553-560, 2012 ASCE International Conference on Computing in Civil Engineering, Clearwater Beach, FL, United States, 6/17/12. https://doi.org/10.1061/9780784412343.0070
Jog GM, Koch C, Golparvar-Fard M, Brilakis I. Pothole properties measurement through visual 2D recognition and 3D reconstruction. In Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering. 2012. p. 553-560. (Congress on Computing in Civil Engineering, Proceedings). https://doi.org/10.1061/9780784412343.0070
Jog, G. M. ; Koch, C. ; Golparvar-Fard, M. ; Brilakis, I. / Pothole properties measurement through visual 2D recognition and 3D reconstruction. Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering. 2012. pp. 553-560 (Congress on Computing in Civil Engineering, Proceedings).
@inproceedings{0a040c9a007b4bcfa14c5604640bfb29,
title = "Pothole properties measurement through visual 2D recognition and 3D reconstruction",
abstract = "Current pavement condition assessment methods are predominantly manual and time consuming. Existing pothole recognition and assessment methods rely on 3D surface reconstruction that requires high equipment and computational costs or relies on acceleration data which provides preliminary results. This paper presents an inexpensive solution that automatically detects and assesses the severity of potholes using vision-based data for both 2D recognition and for 3D reconstruction. The combination of these two techniques is used to improve recognition results by using visual and spatial characteristics of potholes and measure properties (width, number, and depth) that are used to assess severity of potholes. The number of potholes is deduced with 2D recognition whereas the width and depth of the potholes is obtained with 3D reconstruction. The proposed method is validated on several actual potholes. The results show that the proposed inexpensive and visual method holds promise to improve automated pothole detection and severity assessment.",
author = "Jog, {G. M.} and C. Koch and M. Golparvar-Fard and I. Brilakis",
year = "2012",
month = "12",
day = "1",
doi = "10.1061/9780784412343.0070",
language = "English (US)",
isbn = "9780784412343",
series = "Congress on Computing in Civil Engineering, Proceedings",
pages = "553--560",
booktitle = "Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering",

}

TY - GEN

T1 - Pothole properties measurement through visual 2D recognition and 3D reconstruction

AU - Jog, G. M.

AU - Koch, C.

AU - Golparvar-Fard, M.

AU - Brilakis, I.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Current pavement condition assessment methods are predominantly manual and time consuming. Existing pothole recognition and assessment methods rely on 3D surface reconstruction that requires high equipment and computational costs or relies on acceleration data which provides preliminary results. This paper presents an inexpensive solution that automatically detects and assesses the severity of potholes using vision-based data for both 2D recognition and for 3D reconstruction. The combination of these two techniques is used to improve recognition results by using visual and spatial characteristics of potholes and measure properties (width, number, and depth) that are used to assess severity of potholes. The number of potholes is deduced with 2D recognition whereas the width and depth of the potholes is obtained with 3D reconstruction. The proposed method is validated on several actual potholes. The results show that the proposed inexpensive and visual method holds promise to improve automated pothole detection and severity assessment.

AB - Current pavement condition assessment methods are predominantly manual and time consuming. Existing pothole recognition and assessment methods rely on 3D surface reconstruction that requires high equipment and computational costs or relies on acceleration data which provides preliminary results. This paper presents an inexpensive solution that automatically detects and assesses the severity of potholes using vision-based data for both 2D recognition and for 3D reconstruction. The combination of these two techniques is used to improve recognition results by using visual and spatial characteristics of potholes and measure properties (width, number, and depth) that are used to assess severity of potholes. The number of potholes is deduced with 2D recognition whereas the width and depth of the potholes is obtained with 3D reconstruction. The proposed method is validated on several actual potholes. The results show that the proposed inexpensive and visual method holds promise to improve automated pothole detection and severity assessment.

UR - http://www.scopus.com/inward/record.url?scp=84888364100&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888364100&partnerID=8YFLogxK

U2 - 10.1061/9780784412343.0070

DO - 10.1061/9780784412343.0070

M3 - Conference contribution

AN - SCOPUS:84888364100

SN - 9780784412343

T3 - Congress on Computing in Civil Engineering, Proceedings

SP - 553

EP - 560

BT - Computing in Civil Engineering - Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering

ER -