Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization

Yuxuan Hou; Yi Yang; Junbo Wang; Mengyin Fu

doi:10.1109/ITSC55140.2022.9921859

Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization

Yuxuan Hou, Yi Yang^*, Junbo Wang, Mengyin Fu

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Cross-view image-based geo-localization aims to determine the location of ground-view images in satellite images. Most researches regard it as image retrieval problem. However, they don't provide exact location. In this paper, we consider it as a regression problem: given a ground-view image and satellite image, a siamese network finds the location offset between them. The proposed siamese network with fully connected layers can get the offset of satellite center with a ground-view image. Meanwhile, by training road extraction with Dice and Binary Cross Entropy loss, the network can perceive road location and get more accurate result. The experiment of our method gets 16.50 meters mean distance error, 28% less than VIGOR [1] on its dataset.

Original language	English
Title of host publication	2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2934-2940
Number of pages	7
ISBN (Electronic)	9781665468800
DOIs	https://doi.org/10.1109/ITSC55140.2022.9921859
Publication status	Published - 2022
Event	25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 - Macau, China Duration: 8 Oct 2022 → 12 Oct 2022

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volume	2022-October

Conference

Conference	25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022
Country/Territory	China
City	Macau
Period	8/10/22 → 12/10/22

Access to Document

10.1109/ITSC55140.2022.9921859

Cite this

Hou, Y., Yang, Y., Wang, J., & Fu, M. (2022). Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022 (pp. 2934-2940). (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2022-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC55140.2022.9921859

Hou, Yuxuan ; Yang, Yi ; Wang, Junbo et al. / Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization. 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 2934-2940 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

@inproceedings{74a7044295714bd8a57373d07f170553,

title = "Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization",

abstract = "Cross-view image-based geo-localization aims to determine the location of ground-view images in satellite images. Most researches regard it as image retrieval problem. However, they don't provide exact location. In this paper, we consider it as a regression problem: given a ground-view image and satellite image, a siamese network finds the location offset between them. The proposed siamese network with fully connected layers can get the offset of satellite center with a ground-view image. Meanwhile, by training road extraction with Dice and Binary Cross Entropy loss, the network can perceive road location and get more accurate result. The experiment of our method gets 16.50 meters mean distance error, 28% less than VIGOR [1] on its dataset.",

author = "Yuxuan Hou and Yi Yang and Junbo Wang and Mengyin Fu",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 ; Conference date: 08-10-2022 Through 12-10-2022",

year = "2022",

doi = "10.1109/ITSC55140.2022.9921859",

language = "English",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2934--2940",

booktitle = "2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022",

address = "United States",

}

Hou, Y, Yang, Y, Wang, J & Fu, M 2022, Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization. in 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, vol. 2022-October, Institute of Electrical and Electronics Engineers Inc., pp. 2934-2940, 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022, Macau, China, 8/10/22. https://doi.org/10.1109/ITSC55140.2022.9921859

Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization. / Hou, Yuxuan; Yang, Yi; Wang, Junbo et al.
2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 2934-2940 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2022-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization

AU - Hou, Yuxuan

AU - Yang, Yi

AU - Wang, Junbo

AU - Fu, Mengyin

PY - 2022

Y1 - 2022

N2 - Cross-view image-based geo-localization aims to determine the location of ground-view images in satellite images. Most researches regard it as image retrieval problem. However, they don't provide exact location. In this paper, we consider it as a regression problem: given a ground-view image and satellite image, a siamese network finds the location offset between them. The proposed siamese network with fully connected layers can get the offset of satellite center with a ground-view image. Meanwhile, by training road extraction with Dice and Binary Cross Entropy loss, the network can perceive road location and get more accurate result. The experiment of our method gets 16.50 meters mean distance error, 28% less than VIGOR [1] on its dataset.

AB - Cross-view image-based geo-localization aims to determine the location of ground-view images in satellite images. Most researches regard it as image retrieval problem. However, they don't provide exact location. In this paper, we consider it as a regression problem: given a ground-view image and satellite image, a siamese network finds the location offset between them. The proposed siamese network with fully connected layers can get the offset of satellite center with a ground-view image. Meanwhile, by training road extraction with Dice and Binary Cross Entropy loss, the network can perceive road location and get more accurate result. The experiment of our method gets 16.50 meters mean distance error, 28% less than VIGOR [1] on its dataset.

UR - http://www.scopus.com/inward/record.url?scp=85141824344&partnerID=8YFLogxK

U2 - 10.1109/ITSC55140.2022.9921859

DO - 10.1109/ITSC55140.2022.9921859

M3 - Conference contribution

AN - SCOPUS:85141824344

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 2934

EP - 2940

BT - 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022

Y2 - 8 October 2022 through 12 October 2022

ER -

Hou Y, Yang Y, Wang J, Fu M. Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 2934-2940. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC55140.2022.9921859

Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this