eprintid: 4101
rev_number: 15
eprint_status: archive
userid: 422
dir: disk0/00/00/41/01
datestamp: 2021-06-28 00:10:30
lastmod: 2021-06-28 00:10:30
status_changed: 2021-06-28 00:10:30
type: conference_item
metadata_visibility: show
creators_name: Le, Quang Dao
creators_name: Nguyen, Nhat Nam
creators_name: Luu, Quang Thang
creators_name: Ha, Duc Van
creators_name: Ha, Minh Cuong
creators_name: Pham, Bao Son
creators_name: Bui, Quang Hung
creators_id: daolq@fimo.edu.vn
creators_id: namnn@fimo.edu.vn
creators_id: thanglq@fimo.edu.vn
creators_id: vanhd@fimo.edu.vn
creators_id: cuonghm@vnu.edu.vn
creators_id: sonpb@vnu.edu.vn
creators_id: hungbq@fimo.edu.vn
title: Research and application of D-LINKNET network to solve the problem of detecting road from WorldView-3 satellite image in Cau Giay district, Hanoi
ispublished: pub
subjects: IT
subjects: transportation
divisions: FIMO
divisions: sae
abstract: In this paper, we have outlined the need for solving the road detection problem, from which to compare and find the type of data to be used as Worldview-3 satellite images, to find out the method of success. Very good achievement in the DeepGlobe contest is D-LinkNet. This thesis has collected Worldview-3 and yandex image data for preprocessing data. We have collected and pre-processed Worldview-3 data, deployed and installed D-LinkNet. Application of evaluation method of IoU point of DeepGlobe. In addition, learn how to develop a realistic assessment method rather than a long-distance evaluation. D-LinkNet works well in sparsely populated areas, big roads such as suburbs or new urban areas, resettlement areas. In densely populated urban areas, small alleys are obscured by houses and trees, making it difficult and difficult to detect roads. Some areas with the same spectrum as the road are also mislabeled.
date: 2020-12
date_type: published
publisher: Trường Đại học Bách Khoa – ĐHQG-HCM
official_url: https://easychair.org/conferences/profile.cgi?track=260607;a=24818524
full_text_status: public
pres_type: paper
event_title: Hội thảo GIS toàn quốc 2020
event_dates: Tháng 12 năm 2020
event_type: conference
refereed: FALSE
book_title: GIS Conference Proceeding 2020
related_url_url: http://fenr.hcmut.edu.vn/hoi-thao/hoi-thao-gis-toan-quoc-2020-ung-dung-gis-cho-do-thi-thong-minh-huong-toi-phat-trien-ben-vung/n468
related_url_type: org
citation:   Le, Quang Dao and Nguyen, Nhat Nam and Luu, Quang Thang and Ha, Duc Van and Ha, Minh Cuong and Pham, Bao Son and Bui, Quang Hung  (2020) Research and application of D-LINKNET network to solve the problem of detecting road from WorldView-3 satellite image in Cau Giay district, Hanoi.  In: Hội thảo GIS toàn quốc 2020, Tháng 12 năm 2020.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4101/1/gis2020_paper_120%20%282%29.pdf