Riprap Stockpile Size and Shape Analyses Using Computer Vision

Jiayi Luo, Haohang Huang, Issam Qamhia, John M. Hart, Erol Tutumluer

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

Abstract

Riprap rocks and large-sized aggregates are being used extensively in geotechnical and hydraulic engineering applications. Knowing the particle size and morphological/shape properties ensures the reliable and sustainable use of aggregate materials at both quarry production lines and construction sites. Traditional methods for assessing aggregates geometric properties involve subjective visual inspection and time-consuming hand measurements, while the use of computer vision analysis techniques is restricted primarily due to the unwieldiness of large-sized aggregates. This paper presents the use of a computer vision system for in-place size and shape evaluation of large aggregates in a stockpile using images of stockpiles conveniently collected using smartphone cameras. The automated image analysis software is comprised of an image segmentation kernel and a morphological analysis module. Comprehensive analyses are conducted on a sample stockpile with multiple view inspections. Based on the findings of this study, the stockpile aggregate image analysis program has great potential as an efficient and innovative application for field-scale and in-place evaluations of aggregate materials.

Original languageEnglish (US)
Title of host publicationAdvances in Transportation Geotechnics IV - Proceedings of the 4th International Conference on Transportation Geotechnics
EditorsErol Tutumluer, Soheil Nazarian, Imad Al-Qadi, Issam I. A. Qamhia
PublisherSpringer
Pages903-913
Number of pages11
ISBN (Print)9783030772338
DOIs
StatePublished - 2022
Event4th International Conference on Transportation Geotechnics, ICTG 2021 - Chicago, United States
Duration: May 23 2021May 26 2021

Publication series

NameLecture Notes in Civil Engineering
Volume165
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

Conference4th International Conference on Transportation Geotechnics, ICTG 2021
Country/TerritoryUnited States
CityChicago
Period5/23/215/26/21

Keywords

  • Aggregate stockpile
  • Computer vision
  • Deep learning
  • Image segmentation
  • Morphological analyses
  • Object detection
  • Particle size and shape

ASJC Scopus subject areas

  • Civil and Structural Engineering

Fingerprint

Dive into the research topics of 'Riprap Stockpile Size and Shape Analyses Using Computer Vision'. Together they form a unique fingerprint.

Cite this