Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction

Fandel Lin; Craig A. Knoblock; Basel Shbita; Binh Vu; Zekun Li; Yao Yi Chiang

doi:10.1145/3589132.3625659

Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction

Fandel Lin, Craig A. Knoblock, Basel Shbita, Binh Vu, Zekun Li, Yao Yi Chiang

Computer Science and Engineering

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

1 Scopus citations

Abstract

Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.

Original language	English (US)
Title of host publication	31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023
Editors	Maria Luisa Damiani, Matthias Renz, Ahmed Eldawy, Peer Kroger, Mario A. Nascimento
Publisher	Association for Computing Machinery
ISBN (Electronic)	9798400701689
DOIs	https://doi.org/10.1145/3589132.3625659
State	Published - Nov 13 2023
Event	31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 - Hamburg, Germany Duration: Nov 13 2023 → Nov 16 2023

Publication series

Name	GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference

Conference	31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023
Country/Territory	Germany
City	Hamburg
Period	11/13/23 → 11/16/23

Bibliographical note

Publisher Copyright:
© 2023 Owner/Author(s).

Keywords

image processing
polygon extraction
raster map

Publisher link

10.1145/3589132.3625659

Find It

Find It at U of M Libraries

Cite this

Lin, F., Knoblock, C. A., Shbita, B., Vu, B., Li, Z., & Chiang, Y. Y. (2023). Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. In M. L. Damiani, M. Renz, A. Eldawy, P. Kroger, & M. A. Nascimento (Eds.), 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 Article 109 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems). Association for Computing Machinery. https://doi.org/10.1145/3589132.3625659

Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. / Lin, Fandel; Knoblock, Craig A.; Shbita, Basel et al.
31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023. ed. / Maria Luisa Damiani; Matthias Renz; Ahmed Eldawy; Peer Kroger; Mario A. Nascimento. Association for Computing Machinery, 2023. 109 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).

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

Lin, F, Knoblock, CA, Shbita, B, Vu, B, Li, Z & Chiang, YY 2023, Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. in ML Damiani, M Renz, A Eldawy, P Kroger & MA Nascimento (eds), 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023., 109, GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems, Association for Computing Machinery, 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023, Hamburg, Germany, 11/13/23. https://doi.org/10.1145/3589132.3625659

Lin F, Knoblock CA, Shbita B, Vu B, Li Z, Chiang YY. Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. In Damiani ML, Renz M, Eldawy A, Kroger P, Nascimento MA, editors, 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023. Association for Computing Machinery. 2023. 109. (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems). doi: 10.1145/3589132.3625659

Lin, Fandel ; Knoblock, Craig A. ; Shbita, Basel et al. / Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023. editor / Maria Luisa Damiani ; Matthias Renz ; Ahmed Eldawy ; Peer Kroger ; Mario A. Nascimento. Association for Computing Machinery, 2023. (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).

@inproceedings{c9bf01a9f8fd48ddbc7855a5042bd946,

title = "Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction",

abstract = "Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.",

keywords = "image processing, polygon extraction, raster map",

author = "Fandel Lin and Knoblock, {Craig A.} and Basel Shbita and Binh Vu and Zekun Li and Chiang, {Yao Yi}",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author(s).; 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023 ; Conference date: 13-11-2023 Through 16-11-2023",

year = "2023",

month = nov,

day = "13",

doi = "10.1145/3589132.3625659",

language = "English (US)",

series = "GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems",

publisher = "Association for Computing Machinery",

editor = "Damiani, {Maria Luisa} and Matthias Renz and Ahmed Eldawy and Peer Kroger and Nascimento, {Mario A.}",

booktitle = "31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023",

}

TY - GEN

T1 - Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction

AU - Lin, Fandel

AU - Knoblock, Craig A.

AU - Shbita, Basel

AU - Vu, Binh

AU - Li, Zekun

AU - Chiang, Yao Yi

PY - 2023/11/13

Y1 - 2023/11/13

N2 - Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.

AB - Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.

KW - image processing

KW - polygon extraction

KW - raster map

UR - http://www.scopus.com/inward/record.url?scp=85182513691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85182513691&partnerID=8YFLogxK

U2 - 10.1145/3589132.3625659

DO - 10.1145/3589132.3625659

M3 - Conference contribution

AN - SCOPUS:85182513691

T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

BT - 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023

A2 - Damiani, Maria Luisa

A2 - Renz, Matthias

A2 - Eldawy, Ahmed

A2 - Kroger, Peer

A2 - Nascimento, Mario A.

PB - Association for Computing Machinery

T2 - 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2023

Y2 - 13 November 2023 through 16 November 2023

ER -

Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this