Data-driven scene parsing method for construction site monitoring

Hongjo Kim, Kinam Kim, Hyoungkwan Kim

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper presents the applicability of a nonparametric scene parsing model for recognizing all objects in an image. The data-driven model labels all the pixels of query images as their object classes using the labels in similar images of the existing dataset. The model has a flexible number of parameters depending on the size of the training data, it is possible to add or remove new data without re-training the whole model. The capability of the nonparametric model would improve the monitoring performance on the construction site with updating the size of the image dataset over time.

Original languageEnglish
Pages943-947
Number of pages5
Publication statusPublished - 2016 Jan 1
Event33rd International Symposium on Automation and Robotics in Construction, ISARC 2016 - Auburn, United States
Duration: 2016 Jul 182016 Jul 21

Other

Other33rd International Symposium on Automation and Robotics in Construction, ISARC 2016
CountryUnited States
CityAuburn
Period16/7/1816/7/21

Fingerprint

Monitoring
monitoring
Labels
pixel
Pixels
method
parameter

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Civil and Structural Engineering
  • Human-Computer Interaction
  • Geotechnical Engineering and Engineering Geology

Cite this

Kim, H., Kim, K., & Kim, H. (2016). Data-driven scene parsing method for construction site monitoring. 943-947. Paper presented at 33rd International Symposium on Automation and Robotics in Construction, ISARC 2016, Auburn, United States.
Kim, Hongjo ; Kim, Kinam ; Kim, Hyoungkwan. / Data-driven scene parsing method for construction site monitoring. Paper presented at 33rd International Symposium on Automation and Robotics in Construction, ISARC 2016, Auburn, United States.5 p.
@conference{7dfe3360133d42b9ad5019348290356d,
title = "Data-driven scene parsing method for construction site monitoring",
abstract = "This paper presents the applicability of a nonparametric scene parsing model for recognizing all objects in an image. The data-driven model labels all the pixels of query images as their object classes using the labels in similar images of the existing dataset. The model has a flexible number of parameters depending on the size of the training data, it is possible to add or remove new data without re-training the whole model. The capability of the nonparametric model would improve the monitoring performance on the construction site with updating the size of the image dataset over time.",
author = "Hongjo Kim and Kinam Kim and Hyoungkwan Kim",
year = "2016",
month = "1",
day = "1",
language = "English",
pages = "943--947",
note = "33rd International Symposium on Automation and Robotics in Construction, ISARC 2016 ; Conference date: 18-07-2016 Through 21-07-2016",

}

Kim, H, Kim, K & Kim, H 2016, 'Data-driven scene parsing method for construction site monitoring', Paper presented at 33rd International Symposium on Automation and Robotics in Construction, ISARC 2016, Auburn, United States, 16/7/18 - 16/7/21 pp. 943-947.

Data-driven scene parsing method for construction site monitoring. / Kim, Hongjo; Kim, Kinam; Kim, Hyoungkwan.

2016. 943-947 Paper presented at 33rd International Symposium on Automation and Robotics in Construction, ISARC 2016, Auburn, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Data-driven scene parsing method for construction site monitoring

AU - Kim, Hongjo

AU - Kim, Kinam

AU - Kim, Hyoungkwan

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This paper presents the applicability of a nonparametric scene parsing model for recognizing all objects in an image. The data-driven model labels all the pixels of query images as their object classes using the labels in similar images of the existing dataset. The model has a flexible number of parameters depending on the size of the training data, it is possible to add or remove new data without re-training the whole model. The capability of the nonparametric model would improve the monitoring performance on the construction site with updating the size of the image dataset over time.

AB - This paper presents the applicability of a nonparametric scene parsing model for recognizing all objects in an image. The data-driven model labels all the pixels of query images as their object classes using the labels in similar images of the existing dataset. The model has a flexible number of parameters depending on the size of the training data, it is possible to add or remove new data without re-training the whole model. The capability of the nonparametric model would improve the monitoring performance on the construction site with updating the size of the image dataset over time.

UR - http://www.scopus.com/inward/record.url?scp=84994204407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994204407&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84994204407

SP - 943

EP - 947

ER -

Kim H, Kim K, Kim H. Data-driven scene parsing method for construction site monitoring. 2016. Paper presented at 33rd International Symposium on Automation and Robotics in Construction, ISARC 2016, Auburn, United States.