Home > Research > Publications & Outputs > Reconstructing historical urban landscapes from...

Links

Text available via DOI:

View graph of relations

Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City. / Shahtahmassebi, Amir Reza; Huang, Danni; Lu, Jie et al.
In: Remote Sensing Letters, Vol. 15, No. 3, 03.03.2024, p. 280-290.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Shahtahmassebi, AR, Huang, D, Lu, J, Li, E, Huang, X, Jiang, L, Shahtahmassebi, G, Moore, N & Atkinson, PM 2024, 'Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City', Remote Sensing Letters, vol. 15, no. 3, pp. 280-290. https://doi.org/10.1080/2150704x.2024.2320176

APA

Shahtahmassebi, A. R., Huang, D., Lu, J., Li, E., Huang, X., Jiang, L., Shahtahmassebi, G., Moore, N., & Atkinson, P. M. (2024). Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City. Remote Sensing Letters, 15(3), 280-290. https://doi.org/10.1080/2150704x.2024.2320176

Vancouver

Shahtahmassebi AR, Huang D, Lu J, Li E, Huang X, Jiang L et al. Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City. Remote Sensing Letters. 2024 Mar 3;15(3):280-290. Epub 2024 Feb 26. doi: 10.1080/2150704x.2024.2320176

Author

Shahtahmassebi, Amir Reza ; Huang, Danni ; Lu, Jie et al. / Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery : an example of Hangzhou City. In: Remote Sensing Letters. 2024 ; Vol. 15, No. 3. pp. 280-290.

Bibtex

@article{3bbefb0d6e8f4a948ce3eab81b4fe6eb,
title = "Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery: an example of Hangzhou City",
abstract = "Declassified images from the Keyhole (KH)-9 HEXAGON mapping camera system (MCS) offer fine-scale details of urban regions. However, these images have seldom been utilized in urban research due to challenges in labelling (collecting training samples), having only a single panchromatic band and classification. To tackle these limitations, this paper focuses on developing a multi-stage reconstructed historical fine-scale urban landscape (RHFUL) pipeline for KH-9 HEXAGON MCS. The proposed pipeline first integrates internalized parameters, hierarchical object-based image analysis properties and class variability to synthesize new features, abbreviated to IHC. Second, the pipeline uses a weak semi-automated supervised labelling (WSSL) approach to acquire training samples. Finally, the training samples and generated features are subjected to the SegNet deep learning architecture. The performance of each step was assessed against corresponding state-of-the-art benchmark approaches for each of synthesizing features, labelling and classification. In the proposed RHFUL pipeline, the proposed IHC provided the most salient information for urban classification, WSSL labelled urban features more accurately, and the SegNet architecture classified more accurately the urban features relative to the benchmarks. Considering the potential advantages, but also limitations of KH-9 HEXAGON MCS images, further research should be undertaken, particularly drawing on the current advances in pattern recognition techniques for contemporary digital satellite sensors.",
keywords = "Electrical and Electronic Engineering, Earth and Planetary Sciences (miscellaneous)",
author = "Shahtahmassebi, {Amir Reza} and Danni Huang and Jie Lu and Erling Li and Xiaoli Huang and Ling Jiang and Golnaz Shahtahmassebi and Nathan Moore and Atkinson, {Peter M.}",
year = "2024",
month = mar,
day = "3",
doi = "10.1080/2150704x.2024.2320176",
language = "English",
volume = "15",
pages = "280--290",
journal = "Remote Sensing Letters",
issn = "2150-704X",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

RIS

TY - JOUR

T1 - Reconstructing historical urban landscapes from KH-9 HEXAGON mapping camera system imagery

T2 - an example of Hangzhou City

AU - Shahtahmassebi, Amir Reza

AU - Huang, Danni

AU - Lu, Jie

AU - Li, Erling

AU - Huang, Xiaoli

AU - Jiang, Ling

AU - Shahtahmassebi, Golnaz

AU - Moore, Nathan

AU - Atkinson, Peter M.

PY - 2024/3/3

Y1 - 2024/3/3

N2 - Declassified images from the Keyhole (KH)-9 HEXAGON mapping camera system (MCS) offer fine-scale details of urban regions. However, these images have seldom been utilized in urban research due to challenges in labelling (collecting training samples), having only a single panchromatic band and classification. To tackle these limitations, this paper focuses on developing a multi-stage reconstructed historical fine-scale urban landscape (RHFUL) pipeline for KH-9 HEXAGON MCS. The proposed pipeline first integrates internalized parameters, hierarchical object-based image analysis properties and class variability to synthesize new features, abbreviated to IHC. Second, the pipeline uses a weak semi-automated supervised labelling (WSSL) approach to acquire training samples. Finally, the training samples and generated features are subjected to the SegNet deep learning architecture. The performance of each step was assessed against corresponding state-of-the-art benchmark approaches for each of synthesizing features, labelling and classification. In the proposed RHFUL pipeline, the proposed IHC provided the most salient information for urban classification, WSSL labelled urban features more accurately, and the SegNet architecture classified more accurately the urban features relative to the benchmarks. Considering the potential advantages, but also limitations of KH-9 HEXAGON MCS images, further research should be undertaken, particularly drawing on the current advances in pattern recognition techniques for contemporary digital satellite sensors.

AB - Declassified images from the Keyhole (KH)-9 HEXAGON mapping camera system (MCS) offer fine-scale details of urban regions. However, these images have seldom been utilized in urban research due to challenges in labelling (collecting training samples), having only a single panchromatic band and classification. To tackle these limitations, this paper focuses on developing a multi-stage reconstructed historical fine-scale urban landscape (RHFUL) pipeline for KH-9 HEXAGON MCS. The proposed pipeline first integrates internalized parameters, hierarchical object-based image analysis properties and class variability to synthesize new features, abbreviated to IHC. Second, the pipeline uses a weak semi-automated supervised labelling (WSSL) approach to acquire training samples. Finally, the training samples and generated features are subjected to the SegNet deep learning architecture. The performance of each step was assessed against corresponding state-of-the-art benchmark approaches for each of synthesizing features, labelling and classification. In the proposed RHFUL pipeline, the proposed IHC provided the most salient information for urban classification, WSSL labelled urban features more accurately, and the SegNet architecture classified more accurately the urban features relative to the benchmarks. Considering the potential advantages, but also limitations of KH-9 HEXAGON MCS images, further research should be undertaken, particularly drawing on the current advances in pattern recognition techniques for contemporary digital satellite sensors.

KW - Electrical and Electronic Engineering

KW - Earth and Planetary Sciences (miscellaneous)

U2 - 10.1080/2150704x.2024.2320176

DO - 10.1080/2150704x.2024.2320176

M3 - Journal article

VL - 15

SP - 280

EP - 290

JO - Remote Sensing Letters

JF - Remote Sensing Letters

SN - 2150-704X

IS - 3

ER -