eprintid: 3558
rev_number: 7
eprint_status: archive
userid: 285
dir: disk0/00/00/35/58
datestamp: 2019-09-30 04:26:05
lastmod: 2019-09-30 04:26:05
status_changed: 2019-09-30 04:26:05
type: conference_item
metadata_visibility: show
creators_name: Zhu, Qiuchen
creators_name: Dinh, Tran Hiep
creators_name: Phung, Manh Duong
creators_name: Ha, Quang
creators_id: Qiuchen.Zhu@student.uts.edu.au
creators_id: tranhiep.dinh@vnu.edu.vn
creators_id: duongpm@vnu.edu.vn
title: Crack Detection Using Enhanced Thresholding on UAV based Collected Images
ispublished: pub
subjects: ECE
divisions: fac_fet
abstract: This paper proposes a thresholding approach for crack detection in an unmanned aerial vehicle (UAV) based infrastructure inspection system. The proposed algorithm performs recursively on the intensity histogram of UAV-taken images to exploit their crack-pixels appearing at the low intensity interval. A quantified criterion of interclass contrast is proposed and employed as an object cost and stop condition for the recursive process. Experiments on different datasets show that our algorithm outperforms different segmentation approaches to accurately extract crack features of some commercial buildings.
date: 2018-12-05
date_type: published
full_text_status: public
pres_type: paper
event_title: Australian Conference on Robotics and Automation 2018 (ACRA)
event_location: Canterbury, New Zealand
event_dates: 4-6 December, 2018
event_type: conference
refereed: TRUE
citation:   Zhu, Qiuchen and Dinh, Tran Hiep and Phung, Manh Duong and Ha, Quang  (2018) Crack Detection Using Enhanced Thresholding on UAV based Collected Images.  In: Australian Conference on Robotics and Automation 2018 (ACRA), 4-6 December, 2018, Canterbury, New Zealand.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3558/1/1812.07868.pdf