research-article

A weakly supervised approach for estimating spatial density functions from high-resolution satellite imagery

Authors:

Muhammad Usman Rafique,

Ranti Dev SharmaAuthors Info & Claims

SIGSPATIAL '18: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

Pages 33 - 42

https://doi.org/10.1145/3274895.3274934

Published: 06 November 2018 Publication History

Abstract

We propose a neural network component, the regional aggregation layer, that makes it possible to train a pixel-level density estimator using only coarse-grained density aggregates, which reflect the number of objects in an image region. Our approach is simple to use and does not require domain-specific assumptions about the nature of the density function. We evaluate our approach on several synthetic datasets. In addition, we use this approach to learn to estimate high-resolution population and housing density from satellite imagery. In all cases, we find that our approach results in better density estimates than a commonly used baseline. We also show how our housing density estimator can be used to classify buildings as residential or non-residential.

References

[1]

Damian Bargiel. 2017. A new method for crop classification combining time series of radar images and crop phenology information. Remote Sensing of Environment (2017).

[2]

P. Chattopadhyay, R. Vedantam, R. R. Selvaraju, D. Batra, and D. Parikh. 2017. Counting Everyday Objects in Everyday Scenes. In CVPR.

[3]

Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff, Peng Wang, and Hartwig Adam. 2018. MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features. In CVPR.

[4]

Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In ECCV.

[5]

Jerome E Dobson, Edward A Bright, Phillip R Coleman, Richard C Durfee, and Brian A Worley. 2000. LandScan: a global population database for estimating populations at risk. Photogrammetric engineering and remote sensing (2000).

[6]

Patrick Doupe, Emilie Bruzelius, James Faghmous, and Samuel G Ruchman. 2016. Equitable development through deep learning: The case of sub-national population density estimation. In ACM Annual Symposium on Computing for Development.

Digital Library

[7]

Charles Dugas, Yoshua Bengio, François Bélisle, Claude Nadeau, and René Garcia. 2001. Incorporating second-order functional knowledge for better option pricing. In Advances in Neural Information Processing Systems.

Digital Library

[8]

Cory L Eicher and Cynthia A Brewer. 2001. Dasymetric mapping and areal interpolation: Implementation and evaluation. Cartography and Geographic Information Science (2001).

[9]

Facebook Connectivity Lab and Center for International Earth Science Information Network, Columbia University. 2016. High Resolution Settlement Layer. https://www.ciesin.columbia.edu/data/hrsl/ {Online; accessed 5-Sep-2018}.

[10]

Peter F Fisher and Mitchel Langford. 1996. Modeling sensitivity to accuracy in classified imagery: A study of areal interpolation by dasymetric mapping. The Professional Geographer (1996).

[11]

Mingfei Gao, Ang Li, Ruichi Yu, Vlad I Morariu, and Larry S Davis. 2018. C-WSL: Count-guided Weakly Supervised Localization. In ECCV.

[12]

AE Gaughan, Forrest R Stevens, Catherine Linard, Nirav N Patel, and Andrew J Tatem. 2015. Exploring nationally and regionally defined models for large area population mapping. International Journal of Digital Earth (2015).

[13]

Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. 2017. Mask R-CNN. In ICCV.

[14]

James B Holt, CP Lo, and Thomas W Hodler. 2004. Dasymetric estimation of population density and areal interpolation of census data. Cartography and Geographic Information Science (2004).

[15]

Shunping Ji, Chi Zhang, Anjian Xu, Yun Shi, and Yulin Duan. 2018. 3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images. Remote Sensing (2018).

[16]

Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, and Bernt Schiele. 2017. Simple does it: Weakly supervised instance and semantic segmentation. In CVPR.

[17]

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).

[18]

Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical Report. University of Toronto.

[19]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems.

Digital Library

[20]

Nataliia Kussul, Andrii Kolotii, Andrii Shelestov, Bohdan Yailymov, and Mykola Lavreniuk. 2017. Land degradation estimation from global and national satellite based datasets within UN program. In IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications.

[21]

Nataliia Kussul, Mykola Lavreniuk, Sergii Skakun, and Andrii Shelestov. 2017. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters (2017).

[22]

Mitchel Langford and David J Unwin. 1994. Generating and mapping population density surfaces within a geographical information system. The Cartographic Journal (1994).

[23]

Min Lin, Qiang Chen, and Shuicheng Yan. 2013. Network in network. arXiv preprint arXiv:1312.4400 (2013).

[24]

Jeremy Mennis. 2003. Generating surface models of population using dasymetric mapping. The Professional Geographer (2003).

[25]

Daniel Onoro-Rubio and Roberto J López-Sastre. 2016. Towards perspective-free object counting with deep learning. In ECCV.

[26]

Guillem Pascual, Santi Seguí, and Jordi Vitrià. 2018. Uncertainty Gated Network for Land Cover Segmentation. In DeepGlobe (IEEE CVPR Workshop).

[27]

Jose M Pavía and Isidro Cantarino. 2017. Can dasymetric mapping significantly improve population data reallocation in a dense urban area? Geographical Analysis (2017).

[28]

Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, and Jian Sun. 2017. Large Kernel Matters-Improve Semantic Segmentation by Global Convolutional Network. In CVPR.

[29]

Andrea Pomente and David Aleandri. 2017. Convolutional expectation maximization for population estimation. CLEF working notes, CEUR.

[30]

Sashank J Reddi, Satyen Kale, and Sanjiv Kumar. 2018. On the convergence of adam and beyond. In International Conference on Learning Representations.

[31]

Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better, Faster, Stronger. In CVPR.

[32]

Caleb Robinson, Fred Hohman, and Bistra Dilkina. 2017. A Deep Learning Approach for Population Estimation from Satellite Imagery. In ACM SIGSPATIAL Workshop on Geospatial Humanities.

Digital Library

[33]

Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI.

[34]

Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (2015).

Digital Library

[35]

Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).

[36]

Vishwanath A Sindagi and Vishal M Patel. 2017. Generating high-quality crowd density maps using contextual pyramid CNNs. In ICCV.

[37]

Alessandro Sorichetta, Graeme M Hornby, Forrest R Stevens, Andrea E Gaughan, Catherine Linard, and Andrew J Tatem. 2015. High-resolution gridded population datasets for Latin America and the Caribbean in 2010, 2015, and 2020. Scientific Data (2015).

[38]

Forrest R Stevens, Andrea E Gaughan, Catherine Linard, and Andrew J Tatem. 2015. Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data. PLOS ONE (2015).

[39]

John K Wright. 1936. A method of mapping densities of population: With Cape Cod as an example. Geographical Review (1936).

[40]

Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price, and Radomir Mech. 2015. Salient object subitizing. In CVPR.

[41]

Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. 2017. Pyramid Scene Parsing Network. In CVPR.

[42]

Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR.

[43]

Yanzhao Zhou, Yi Zhu, Qixiang Ye, Qiang Qiu, and Jianbin Jiao. 2018. Weakly Supervised Instance Segmentation using Class Peak Response. In CVPR.

[44]

Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V Le. 2018. Learning Transferable Architectures for Scalable Image Recognition. In CVPR.

Cited By

Xia JLi RLiu XLiu GPeng M(2024)Scale effects-aware bottom-up population estimation using weakly supervised learningInternational Journal of Digital Earth10.1080/17538947.2024.234178817:1Online publication date: 16-Apr-2024
https://doi.org/10.1080/17538947.2024.2341788
Doda SKahl MOuan KObadic IWang YTaubenböck HZhu X(2024)Interpretable deep learning for consistent large-scale urban population estimation using Earth observation dataInternational Journal of Applied Earth Observation and Geoinformation10.1016/j.jag.2024.103731128(103731)Online publication date: May-2024
https://doi.org/10.1016/j.jag.2024.103731
Workman SHadzic ARafique M(2023)Handling Image and Label Resolution Mismatch in Remote Sensing2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV56688.2023.00370(3698-3707)Online publication date: Jan-2023
https://doi.org/10.1109/WACV56688.2023.00370
Show More Cited By

Index Terms

A weakly supervised approach for estimating spatial density functions from high-resolution satellite imagery
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Information systems
  1. Information systems applications
    1. Spatial-temporal systems
      1. Geographic information systems

Recommendations

A population density grid for Spain

This article describes a high-resolution land cover data set for Spain and its application to dasymetric population mapping at census tract level. Eventually, this vector layer is transformed into a grid format. The work parallels the effort of the ...
Extracting forest canopy structure from spatial information of high resolution optical imagery: tree crown size versus leaf area index

Leaves are the primary interface where energy, water and carbon exchanges occur between the forest ecosystems and the atmosphere. Leaf area index (LAI) is a measure of the amount of leaf area in a stand, and the tree crown size characterizes how leaves ...
Estimating tree crown size with spatial information of high resolution optical remotely sensed imagery

Tree crown size is a critical biophysical parameter that influences carbon, water and energy exchanges between forest ecosystems and the atmosphere. This study explores the potential of using spatial information of high resolution optical imagery in ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGSPATIAL '18: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

November 2018

655 pages

ISBN:9781450358897

DOI:10.1145/3274895

General Chairs:
Farnoush Banaei-Kashani
University of Colorado, Denver
,
Erik Hoel
Esri
,
Program Chairs:
Ralf Hartmut Güting
FernUniversität in Hagen, Germany
,
Roberto Tamassia
Brown University
,
Li Xiong
Emory University

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGSPATIAL: ACM Special Interest Group on Spatial Information

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 November 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

SIGSPATIAL '18

Sponsor:

SIGSPATIAL

SIGSPATIAL '18: 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

November 6 - 9, 2018

Washington, Seattle

Acceptance Rates

SIGSPATIAL '18 Paper Acceptance Rate 30 of 150 submissions, 20%;

Overall Acceptance Rate 220 of 1,116 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
156
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)2

Reflects downloads up to 26 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Xia JLi RLiu XLiu GPeng M(2024)Scale effects-aware bottom-up population estimation using weakly supervised learningInternational Journal of Digital Earth10.1080/17538947.2024.234178817:1Online publication date: 16-Apr-2024
https://doi.org/10.1080/17538947.2024.2341788
Doda SKahl MOuan KObadic IWang YTaubenböck HZhu X(2024)Interpretable deep learning for consistent large-scale urban population estimation using Earth observation dataInternational Journal of Applied Earth Observation and Geoinformation10.1016/j.jag.2024.103731128(103731)Online publication date: May-2024
https://doi.org/10.1016/j.jag.2024.103731
Workman SHadzic ARafique M(2023)Handling Image and Label Resolution Mismatch in Remote Sensing2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV56688.2023.00370(3698-3707)Online publication date: Jan-2023
https://doi.org/10.1109/WACV56688.2023.00370
Archbold CBrodie BOgholbake AJacobs N(2023)Fine-Grained Property Value Assessment Using Probabilistic DisaggregationIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium10.1109/IGARSS52108.2023.10283436(5312-5315)Online publication date: 16-Jul-2023
https://doi.org/10.1109/IGARSS52108.2023.10283436
Paudel DMarcos Dde Wit ABoogaard HAthanasiadis I(2023)A weakly supervised framework for high-resolution crop yield forecastsEnvironmental Research Letters10.1088/1748-9326/acf50e18:9(094062)Online publication date: 18-Sep-2023
https://doi.org/10.1088/1748-9326/acf50e
Monteiro JMartins BCosta MPires JRenz MSarwat M(2022)A co-training approach for spatial data disaggregationProceedings of the 30th International Conference on Advances in Geographic Information Systems10.1145/3557915.3561475(1-10)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1145/3557915.3561475
Metzger NVargas-Muñoz JDaudt RKellenberger BWhelan TOfli FImran MSchindler KTuia D(2022)Fine-grained population mapping from coarse census counts and open geodataScientific Reports10.1038/s41598-022-24495-w12:1Online publication date: 22-Nov-2022
https://doi.org/10.1038/s41598-022-24495-w
Monteiro JMartins BCosta MPires J(2021)Geospatial Data Disaggregation through Self-Trained Encoder–Decoder Convolutional ModelsISPRS International Journal of Geo-Information10.3390/ijgi1009061910:9(619)Online publication date: 16-Sep-2021
https://doi.org/10.3390/ijgi10090619
Hadzic AChristie GFreeman JDismer ABullard SGreiner AJacobs NMukherjee R(2020)Estimating Displaced Populations from OverheadIGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium10.1109/IGARSS39084.2020.9324617(1121-1124)Online publication date: 26-Sep-2020
https://doi.org/10.1109/IGARSS39084.2020.9324617
Workman SJacobs N(2020)Dynamic Traffic Modeling From Overhead Imagery2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR42600.2020.01233(12312-12321)Online publication date: Jul-2020
https://doi.org/10.1109/CVPR42600.2020.01233

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents