%0 Conference Paper %1 budig2016polygon %A Budig, Benedikt %A Van Dijk, Thomas C. %A Feitsch, Fabian %A Giraldo Arteaga, Mauricio %B Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2016) %D 2016 %K historicalmaps myown polygonconsensus sysrelevantforcsuniwue %P 66:1--66:4 %T Polygon Consensus: Smart Crowdsourcing for Extracting Building Footprints from Historical Maps %U http://www1.pub.informatik.uni-wuerzburg.de/pub/budig/papers/ACM-SIGSPATIAL-2016_Budig_VanDijk_Feitsch_GiraldoArteaga.pdf %X Over the course of three years, the New York Public Library has run a crowdsourcing project to extract polygonal representation of the building footprints from insurance atlases of the 19th and early-20th century. As is common in crowdsourcing projects, the overall problem was decomposed into small user tasks and each task was given to multiple users. In the case of polygons representing building footprints, it is unclear how best to integrate the answers into a majority vote: given a set of polygons ostensibly describing the same footprint, what is the consensus? We discuss desirable properties of such a "consensus polygon" and arrive at an efficient algorithm. We have manually evaluated the algorithm on approximately 3,000 polygons corresponding to 200 footprints and observe that our algorithmic consensus polygons are correct for 96% of the footprints whereas only 85% of the (input) crowd polygons are correct.

@inproceedings{budig2016polygon, abstract = {Over the course of three years, the New York Public Library has run a crowdsourcing project to extract polygonal representation of the building footprints from insurance atlases of the 19th and early-20th century. As is common in crowdsourcing projects, the overall problem was decomposed into small user tasks and each task was given to multiple users. In the case of polygons representing building footprints, it is unclear how best to integrate the answers into a majority vote: given a set of polygons ostensibly describing the same footprint, what is the consensus? We discuss desirable properties of such a "consensus polygon" and arrive at an efficient algorithm. We have manually evaluated the algorithm on approximately 3,000 polygons corresponding to 200 footprints and observe that our algorithmic consensus polygons are correct for 96% of the footprints whereas only 85% of the (input) crowd polygons are correct.}, added-at = {2016-11-14T14:04:40.000+0100}, author = {Budig, Benedikt and Van Dijk, Thomas C. and Feitsch, Fabian and Giraldo Arteaga, Mauricio}, biburl = {https://www.bibsonomy.org/bibtex/24c02ba99dffddf26d019a28dcec6be17/benedikt.budig}, booktitle = {Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2016)}, interhash = {dffdacb263d318c5a3ce4fdef1042290}, intrahash = {4c02ba99dffddf26d019a28dcec6be17}, keywords = {historicalmaps myown polygonconsensus sysrelevantforcsuniwue}, pages = {66:1--66:4}, timestamp = {2017-07-03T11:51:16.000+0200}, title = {Polygon Consensus: Smart Crowdsourcing for Extracting Building Footprints from Historical Maps}, url = {http://www1.pub.informatik.uni-wuerzburg.de/pub/budig/papers/ACM-SIGSPATIAL-2016_Budig_VanDijk_Feitsch_GiraldoArteaga.pdf}, year = 2016 }