I-RIPRAP 3D Image Analysis Software: User Manual

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

doi:10.36501/0197-9191/23-008

i

I-RIPRAP 3D Image Analysis Software: User Manual

2023-06-01
By Huang, Haohang ; Luo, Jiayi ; Ding, Kelin

File Language:

English

Details

Creators:

Huang, Haohang ; Luo, Jiayi ; Ding, Kelin ; Tutumluer, Erol ; Hart, John M. ; Qamhia, Issam
Corporate Creators:

Illinois Center for Transportation ; University of Illinois at Urbana-Champaign
Corporate Contributors:

Illinois. Department of Transportation ; United States. Department of Transportation. Federal Highway Administration
Subject/TRT Terms:
Publication/ Report Number:

FHWA-ICT-23-007
DOI:

https://doi.org/10.36501/0197-9191/23-008
Resource Type:

Manual
Geographical Coverage:

United States
Corporate Publisher:

Illinois Center for Transportation
Description:

This research study introduces a new approach based on deep learning techniques that combines three developed research components: field 3D reconstruction procedures, 3D stockpiles instance segmentation, and 3D shape completion. The approach is designed to reconstruct aggregate stockpiles from multiple images, segment the stockpile into individual instances, and predict the unseen sides of each instance (particle) based on the partially visible shapes. The approach was validated using ground-truth measurements and demonstrated satisfactory algorithm performance in capturing and predicting the unseen sides of aggregates.
Format:

PDF
Download URL:

https://rosap.ntl.bts.gov/view/dot/67694/dot_67694_DS1.pdf
File Type:

[PDF - 2.93 MB]
Collection(s):

US Transportation Collection
Main Document Checksum:

urn:sha-512:08c8cacb1fc11133c13121d6e0237509e11753f7dbb966db7f7c505468f18652df70f64a803c99552c482aec1bea75b688afff498b00aa89e06bfb3bbad5aa5e

File Language:

English

ON THIS PAGE

Details Related Documents

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.