TY  - CONF
ID  - SisLab4101
UR  - https://easychair.org/conferences/profile.cgi?track=260607;a=24818524
A1  - Le, Quang Dao
A1  - Nguyen, Nhat Nam
A1  - Luu, Quang Thang
A1  - Ha, Duc Van
A1  - Ha, Minh Cuong
A1  - Pham, Bao Son
A1  - Bui, Quang Hung
Y1  - 2020/12//
N2  - 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.
PB  - Tr??ng ??i h?c Ba?ch Khoa ? ?HQG-HCM
TI  - Research and application of D-LINKNET network to solve the problem of detecting road from WorldView-3 satellite image in Cau Giay district, Hanoi
AV  - public
T2  - H?i th?o GIS toàn qu?c 2020
ER  -