Automatic alignment of geographic features in contemporary vector data and historical maps

Weiwei Duan, Yao Yi Chiang, Craig A. Knoblock, Vinil Jain, Dan Feldman, Johannes H. Uhl, Stefan Leyk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Scopus citations

Abstract

With large amounts of digital map archives becoming available, the capability to automatically extracting information from historical maps is important for many domains that require long-term geographic data, such as understanding the development of the landscape and human activities. In the previous work, we built a system to automatically recognize geographic features in historical maps using Convolutional Neural Networks (CNN). Our system uses contemporary vector data to automatically label examples of the geographic feature of interest in historical maps as training samples for the CNN model. The alignment between the vector data and geographic features in maps controls if the system can generate representative training samples, which has a significant impact on recognition performance of the system. Due to the large number of training data that the CNN model needs and tens of thousands of maps needed to be processed in an archive, manually aligning the vector data to each map in an archive is not practical. In this paper, we present an algorithm that automatically aligns vector data with geographic features in historical maps. Existing alignment approaches focus on road features and imagery and are difficult to generalize for other geographic features. Our algorithm aligns various types of geographic features in document images with the corresponding vector data. In the experiment, our alignment algorithm increased the correctness and completeness of the extracted railroad and river vector data for about 100% and 20%, respectively. For the performance of feature recognition, the aligned vector data had a 100% improvement on the precision while maintained a similar recall.

Original languageEnglish (US)
Title of host publicationProceedings of the 1st Workshop on GeoAI
Subtitle of host publicationAI and Deep Learning for Geographic Knowledge Discovery, GeoAI 2017
PublisherAssociation for Computing Machinery, Inc
Pages45-54
Number of pages10
ISBN (Electronic)9781450354981
DOIs
StatePublished - Nov 7 2017
Externally publishedYes
Event1st Workshop on GeoAI: AI and Deep Learning for Geographic Knowledge Discovery, GeoAI 2017 - Los Angeles, United States
Duration: Nov 7 2017Nov 10 2017

Publication series

NameProceedings of the 1st Workshop on GeoAI: AI and Deep Learning for Geographic Knowledge Discovery, GeoAI 2017

Conference

Conference1st Workshop on GeoAI: AI and Deep Learning for Geographic Knowledge Discovery, GeoAI 2017
Country/TerritoryUnited States
CityLos Angeles
Period11/7/1711/10/17

Bibliographical note

Funding Information:
For the feature recognition system, we are going to improve the recognition performance in two ways. In the experiment, we found that many false positives were very similar to the true positives within the window. Hence, one way that we plan to improve the system is to try different window sizes to find more representative training samples. In the related work, we found some researchers use DNN to extract geographic features, which has good performance. We plan to build a DNN model and test if the model can improve the recognition performance. ACKNOWLEDGEMENTS This material is based on research supported in part by the National Science Foundation under Grant No. IIS 1563933 (to the Univesity of Colorado at Boulder) and IIS 1564164 (to the university of Southern California). We gratefully acknowledge the support of Microsoft Corporation with the Azure for Research Award and NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.

Funding Information:
This material is based on research supported in part by the National Science Foundation under Grant No. IIS 1563933 (to the Univesity of Colorado at Boulder) and IIS 1564164 (to the university of Southern California). We gratefully acknowledge the support of Microsoft Corporation with the Azure for Research Award and NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.

Publisher Copyright:
© 2017 Association for Computing Machinery.

Keywords

  • Historical documents
  • Map processing
  • Vector data alignment

Fingerprint

Dive into the research topics of 'Automatic alignment of geographic features in contemporary vector data and historical maps'. Together they form a unique fingerprint.

Cite this