Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks
Information extraction from historical maps represents a persistent challenge due to inferior graphical quality and the large data volume of digital map archives, which can hold thousands of digitized map sheets. Traditional map processing techniques typically rely on manually collected templates of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8946322/ |
| _version_ | 1818857080801460224 |
|---|---|
| author | Johannes H. Uhl Stefan Leyk Yao-Yi Chiang Weiwei Duan Craig A. Knoblock |
| author_facet | Johannes H. Uhl Stefan Leyk Yao-Yi Chiang Weiwei Duan Craig A. Knoblock |
| author_sort | Johannes H. Uhl |
| collection | DOAJ |
| description | Information extraction from historical maps represents a persistent challenge due to inferior graphical quality and the large data volume of digital map archives, which can hold thousands of digitized map sheets. Traditional map processing techniques typically rely on manually collected templates of the symbol of interest, and thus are not suitable for large-scale information extraction. In order to digitally preserve such large amounts of valuable retrospective geographic information, high levels of automation are required. Herein, we propose an automated machine-learning based framework to extract human settlement symbols, such as buildings and urban areas from historical topographic maps in the absence of training data, employing contemporary geospatial data as ancillary data to guide the collection of training samples. These samples are then used to train a convolutional neural network for semantic image segmentation, allowing for the extraction of human settlement patterns in an analysis-ready geospatial vector data format. We test our method on United States Geological Survey historical topographic maps published between 1893 and 1954. The results are promising, indicating high degrees of completeness in the extracted settlement features (i.e., recall of up to 0.96, F-measure of up to 0.79) and will guide the next steps to provide a fully automated operational approach for large-scale geographic feature extraction from a variety of historical map series. Moreover, the proposed framework provides a robust approach for the recognition of objects which are small in size, generalizable to many kinds of visual documents. |
| first_indexed | 2024-12-19T08:34:43Z |
| format | Article |
| id | doaj.art-8fb6daa8dd2d44d5bbf6fab661df7a8b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T08:34:43Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8fb6daa8dd2d44d5bbf6fab661df7a8b2022-12-21T20:29:04ZengIEEEIEEE Access2169-35362020-01-0186978699610.1109/ACCESS.2019.29632138946322Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural NetworksJohannes H. Uhl0https://orcid.org/0000-0002-4861-5915Stefan Leyk1https://orcid.org/0000-0001-9180-4853Yao-Yi Chiang2https://orcid.org/0000-0002-8923-0130Weiwei Duan3https://orcid.org/0000-0002-7162-5310Craig A. Knoblock4https://orcid.org/0000-0002-6371-4807Department of Geography, University of Colorado Boulder, Boulder, CO, USADepartment of Geography, University of Colorado Boulder, Boulder, CO, USASpatial Sciences Institute, University of Southern California, Los Angeles, CA, USASpatial Sciences Institute, University of Southern California, Los Angeles, CA, USASpatial Sciences Institute, University of Southern California, Los Angeles, CA, USAInformation extraction from historical maps represents a persistent challenge due to inferior graphical quality and the large data volume of digital map archives, which can hold thousands of digitized map sheets. Traditional map processing techniques typically rely on manually collected templates of the symbol of interest, and thus are not suitable for large-scale information extraction. In order to digitally preserve such large amounts of valuable retrospective geographic information, high levels of automation are required. Herein, we propose an automated machine-learning based framework to extract human settlement symbols, such as buildings and urban areas from historical topographic maps in the absence of training data, employing contemporary geospatial data as ancillary data to guide the collection of training samples. These samples are then used to train a convolutional neural network for semantic image segmentation, allowing for the extraction of human settlement patterns in an analysis-ready geospatial vector data format. We test our method on United States Geological Survey historical topographic maps published between 1893 and 1954. The results are promising, indicating high degrees of completeness in the extracted settlement features (i.e., recall of up to 0.96, F-measure of up to 0.79) and will guide the next steps to provide a fully automated operational approach for large-scale geographic feature extraction from a variety of historical map series. Moreover, the proposed framework provides a robust approach for the recognition of objects which are small in size, generalizable to many kinds of visual documents.https://ieeexplore.ieee.org/document/8946322/Convolutional neural networksdigital humanitiesdigital preservationdocument analysisgeospatial analysisgeospatial artificial intelligence |
| spellingShingle | Johannes H. Uhl Stefan Leyk Yao-Yi Chiang Weiwei Duan Craig A. Knoblock Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks IEEE Access Convolutional neural networks digital humanities digital preservation document analysis geospatial analysis geospatial artificial intelligence |
| title | Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks |
| title_full | Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks |
| title_fullStr | Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks |
| title_full_unstemmed | Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks |
| title_short | Automated Extraction of Human Settlement Patterns From Historical Topographic Map Series Using Weakly Supervised Convolutional Neural Networks |
| title_sort | automated extraction of human settlement patterns from historical topographic map series using weakly supervised convolutional neural networks |
| topic | Convolutional neural networks digital humanities digital preservation document analysis geospatial analysis geospatial artificial intelligence |
| url | https://ieeexplore.ieee.org/document/8946322/ |
| work_keys_str_mv | AT johanneshuhl automatedextractionofhumansettlementpatternsfromhistoricaltopographicmapseriesusingweaklysupervisedconvolutionalneuralnetworks AT stefanleyk automatedextractionofhumansettlementpatternsfromhistoricaltopographicmapseriesusingweaklysupervisedconvolutionalneuralnetworks AT yaoyichiang automatedextractionofhumansettlementpatternsfromhistoricaltopographicmapseriesusingweaklysupervisedconvolutionalneuralnetworks AT weiweiduan automatedextractionofhumansettlementpatternsfromhistoricaltopographicmapseriesusingweaklysupervisedconvolutionalneuralnetworks AT craigaknoblock automatedextractionofhumansettlementpatternsfromhistoricaltopographicmapseriesusingweaklysupervisedconvolutionalneuralnetworks |