MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY

Sining Chen; Lichao Mou; Qingyu Li; Yao Sun; Xiao Xiang Zhu

doi:10.1109/IGARSS47720.2021.9553121

MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY

Sining Chen, Lichao Mou, Qingyu Li, Yao Sun, Xiao Xiang Zhu

Chair of Data Science in Earth Observation

Technical University of Munich

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

9 Scopus citations

Abstract

3D building reconstruction from monocular remote sensing imagery is a promising and economical way to generate 3D city models at a large scale, yet the task is rarely touched. The paper tackles the problem via an end-to-end network. The goal is achieved by a modified network, named Mask-Height R-CNN, based on Mask R-CNN, with an additional height prediction head in the Region Proposal Network (RPN). Unlike most deep learning based methods, the height estimation is done on the instance level instead of pixel level, which does not require the assembly of the height maps and building masks. The proposed network gains good performances on ISPRS datasets, with 3D F1 scores of over 0.8.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1202-1205
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553121
State	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: 12 Jul 2021 → 16 Jul 2021

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	12/07/21 → 16/07/21

Keywords

Building reconstruction
Footprint extraction
Height estimation
Monocular imagery

Access to Document

10.1109/IGARSS47720.2021.9553121

Cite this

Chen, S., Mou, L., Li, Q., Sun, Y., & Zhu, X. X. (2021). MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 1202-1205). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9553121

Chen, Sining ; Mou, Lichao ; Li, Qingyu et al. / MASK-HEIGHT R-CNN : AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY. IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 1202-1205 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{53ed05090ebc4781826f219c6c4ef2b9,

title = "MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY",

abstract = "3D building reconstruction from monocular remote sensing imagery is a promising and economical way to generate 3D city models at a large scale, yet the task is rarely touched. The paper tackles the problem via an end-to-end network. The goal is achieved by a modified network, named Mask-Height R-CNN, based on Mask R-CNN, with an additional height prediction head in the Region Proposal Network (RPN). Unlike most deep learning based methods, the height estimation is done on the instance level instead of pixel level, which does not require the assembly of the height maps and building masks. The proposed network gains good performances on ISPRS datasets, with 3D F1 scores of over 0.8.",

keywords = "Building reconstruction, Footprint extraction, Height estimation, Monocular imagery",

author = "Sining Chen and Lichao Mou and Qingyu Li and Yao Sun and Zhu, {Xiao Xiang}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553121",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "1202--1205",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Chen, S, Mou, L, Li, Q, Sun, Y & Zhu, XX 2021, MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., pp. 1202-1205, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 12/07/21. https://doi.org/10.1109/IGARSS47720.2021.9553121

MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY. / Chen, Sining; Mou, Lichao; Li, Qingyu et al.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 1202-1205 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

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

TY - GEN

T1 - MASK-HEIGHT R-CNN

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

AU - Chen, Sining

AU - Mou, Lichao

AU - Li, Qingyu

AU - Sun, Yao

AU - Zhu, Xiao Xiang

PY - 2021

Y1 - 2021

N2 - 3D building reconstruction from monocular remote sensing imagery is a promising and economical way to generate 3D city models at a large scale, yet the task is rarely touched. The paper tackles the problem via an end-to-end network. The goal is achieved by a modified network, named Mask-Height R-CNN, based on Mask R-CNN, with an additional height prediction head in the Region Proposal Network (RPN). Unlike most deep learning based methods, the height estimation is done on the instance level instead of pixel level, which does not require the assembly of the height maps and building masks. The proposed network gains good performances on ISPRS datasets, with 3D F1 scores of over 0.8.

AB - 3D building reconstruction from monocular remote sensing imagery is a promising and economical way to generate 3D city models at a large scale, yet the task is rarely touched. The paper tackles the problem via an end-to-end network. The goal is achieved by a modified network, named Mask-Height R-CNN, based on Mask R-CNN, with an additional height prediction head in the Region Proposal Network (RPN). Unlike most deep learning based methods, the height estimation is done on the instance level instead of pixel level, which does not require the assembly of the height maps and building masks. The proposed network gains good performances on ISPRS datasets, with 3D F1 scores of over 0.8.

KW - Building reconstruction

KW - Footprint extraction

KW - Height estimation

KW - Monocular imagery

UR - http://www.scopus.com/inward/record.url?scp=85119820940&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9553121

DO - 10.1109/IGARSS47720.2021.9553121

M3 - Conference contribution

AN - SCOPUS:85119820940

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1202

EP - 1205

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 12 July 2021 through 16 July 2021

ER -

Chen S, Mou L, Li Q, Sun Y, Zhu XX. MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 1202-1205. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS47720.2021.9553121

MASK-HEIGHT R-CNN: AN END-TO-END NETWORK FOR 3D BUILDING RECONSTRUCTION FROM MONOCULAR REMOTE SENSING IMAGERY

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this