Multi-label building functions classification from ground pictures using convolutional neural networks

S. Srivastava, John E. Vargas Muñoz, David Swinkels, D. Tuia

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

1 Citation (Scopus)

Abstract

We approach the problem of multi building function classification for buildings from the city of Amsterdam using a collection of Google Street View (GSV) pictures acquired at multiple zoom levels (field of views, FoV) and the corresponding governmental census data per building. Since buildings can have multiple usages, we cast the problem as multilabel classification task. To do so, we trained a CNN model end-to-end with the task of predicting multiple co-occurring building function classes per building. We fuse the individual features of three FoVs by using volumetric stacking. Our proposed model outperforms baseline CNN models that use either single or multiple FoVs.
Original languageEnglish
Title of host publicationProceedings of the 2nd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery
Place of PublicationNew York
PublisherACM
Pages43-46
ISBN (Print)9781450360364
DOIs
Publication statusPublished - 6 Nov 2018
Event2nd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery - Seattle, United States
Duration: 6 Nov 20186 Nov 2018
https://udi.ornl.gov/geoai

Conference

Conference2nd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery
Abbreviated titleGeoAI'18
CountryUnited States
CitySeattle
Period6/11/186/11/18
Internet address

    Fingerprint

Cite this

Srivastava, S., Vargas Muñoz, J. E., Swinkels, D., & Tuia, D. (2018). Multi-label building functions classification from ground pictures using convolutional neural networks. In Proceedings of the 2nd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (pp. 43-46). New York: ACM. https://doi.org/10.1145/3281548.3281559