An image augmentation method for detecting construction resources using convolutional neural network and UAV images

S. Bang, F. Baek, S. Park, W. Kim, H. Kim

Research output: Contribution to conferencePaper

Abstract

Images acquired by UAV can be analyzed for resource management on construction sites. However, analyzing the construction site images acquired by UAV is difficult due to the characteristics of UAV images and construction site images. This paper proposes an image augmentation method to improve the performance of an object detection model for construction site images acquired by UAV. The method consists of three techniques: intensity variation, image smoothing, and scale transformation. Experimental results show that the method can improve the performance of the detection model (Faster R-CNN) by achieving a recall and a precision of 53.08% and 66.76%, respectively. With future studies, the method is expected to contribute to UAV-based resource management on construction sites.

Original languageEnglish
Pages639-644
Number of pages6
Publication statusPublished - 2019 Jan 1
Event36th International Symposium on Automation and Robotics in Construction, ISARC 2019 - Banff, Canada
Duration: 2019 May 212019 May 24

Conference

Conference36th International Symposium on Automation and Robotics in Construction, ISARC 2019
CountryCanada
CityBanff
Period19/5/2119/5/24

Fingerprint

Unmanned aerial vehicles (UAV)
Neural networks

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Building and Construction
  • Human-Computer Interaction

Cite this

Bang, S., Baek, F., Park, S., Kim, W., & Kim, H. (2019). An image augmentation method for detecting construction resources using convolutional neural network and UAV images. 639-644. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.
Bang, S. ; Baek, F. ; Park, S. ; Kim, W. ; Kim, H. / An image augmentation method for detecting construction resources using convolutional neural network and UAV images. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.6 p.
@conference{29db6c546ea34f23b2637b87da3c8974,
title = "An image augmentation method for detecting construction resources using convolutional neural network and UAV images",
abstract = "Images acquired by UAV can be analyzed for resource management on construction sites. However, analyzing the construction site images acquired by UAV is difficult due to the characteristics of UAV images and construction site images. This paper proposes an image augmentation method to improve the performance of an object detection model for construction site images acquired by UAV. The method consists of three techniques: intensity variation, image smoothing, and scale transformation. Experimental results show that the method can improve the performance of the detection model (Faster R-CNN) by achieving a recall and a precision of 53.08{\%} and 66.76{\%}, respectively. With future studies, the method is expected to contribute to UAV-based resource management on construction sites.",
author = "S. Bang and F. Baek and S. Park and W. Kim and H. Kim",
year = "2019",
month = "1",
day = "1",
language = "English",
pages = "639--644",
note = "36th International Symposium on Automation and Robotics in Construction, ISARC 2019 ; Conference date: 21-05-2019 Through 24-05-2019",

}

Bang, S, Baek, F, Park, S, Kim, W & Kim, H 2019, 'An image augmentation method for detecting construction resources using convolutional neural network and UAV images', Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada, 19/5/21 - 19/5/24 pp. 639-644.

An image augmentation method for detecting construction resources using convolutional neural network and UAV images. / Bang, S.; Baek, F.; Park, S.; Kim, W.; Kim, H.

2019. 639-644 Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.

Research output: Contribution to conferencePaper

TY - CONF

T1 - An image augmentation method for detecting construction resources using convolutional neural network and UAV images

AU - Bang, S.

AU - Baek, F.

AU - Park, S.

AU - Kim, W.

AU - Kim, H.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Images acquired by UAV can be analyzed for resource management on construction sites. However, analyzing the construction site images acquired by UAV is difficult due to the characteristics of UAV images and construction site images. This paper proposes an image augmentation method to improve the performance of an object detection model for construction site images acquired by UAV. The method consists of three techniques: intensity variation, image smoothing, and scale transformation. Experimental results show that the method can improve the performance of the detection model (Faster R-CNN) by achieving a recall and a precision of 53.08% and 66.76%, respectively. With future studies, the method is expected to contribute to UAV-based resource management on construction sites.

AB - Images acquired by UAV can be analyzed for resource management on construction sites. However, analyzing the construction site images acquired by UAV is difficult due to the characteristics of UAV images and construction site images. This paper proposes an image augmentation method to improve the performance of an object detection model for construction site images acquired by UAV. The method consists of three techniques: intensity variation, image smoothing, and scale transformation. Experimental results show that the method can improve the performance of the detection model (Faster R-CNN) by achieving a recall and a precision of 53.08% and 66.76%, respectively. With future studies, the method is expected to contribute to UAV-based resource management on construction sites.

UR - http://www.scopus.com/inward/record.url?scp=85071458783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071458783&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85071458783

SP - 639

EP - 644

ER -

Bang S, Baek F, Park S, Kim W, Kim H. An image augmentation method for detecting construction resources using convolutional neural network and UAV images. 2019. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.