Standard

Crowd-Mapping Urban Objects from Street-Level Imagery. / Qiu, Sihang; Psyllidis, Achilleas; Bozzon, Alessandro; Houben, Geert-Jan.

Proceedings of the 2019 World Wide Web Conference. New York, NY : Association for Computing Machinery (ACM), 2019. p. 1521-1531.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Qiu, S, Psyllidis, A, Bozzon, A & Houben, G-J 2019, Crowd-Mapping Urban Objects from Street-Level Imagery. in Proceedings of the 2019 World Wide Web Conference. Association for Computing Machinery (ACM), New York, NY, pp. 1521-1531, WWW 2019 , San Francisco, CA, United States, 13/05/19. https://doi.org/10.1145/3308558.3313651

APA

Qiu, S., Psyllidis, A., Bozzon, A., & Houben, G-J. (2019). Crowd-Mapping Urban Objects from Street-Level Imagery. In Proceedings of the 2019 World Wide Web Conference (pp. 1521-1531). New York, NY: Association for Computing Machinery (ACM). https://doi.org/10.1145/3308558.3313651

Vancouver

Qiu S, Psyllidis A, Bozzon A, Houben G-J. Crowd-Mapping Urban Objects from Street-Level Imagery. In Proceedings of the 2019 World Wide Web Conference. New York, NY: Association for Computing Machinery (ACM). 2019. p. 1521-1531 https://doi.org/10.1145/3308558.3313651

Author

Qiu, Sihang ; Psyllidis, Achilleas ; Bozzon, Alessandro ; Houben, Geert-Jan. / Crowd-Mapping Urban Objects from Street-Level Imagery. Proceedings of the 2019 World Wide Web Conference. New York, NY : Association for Computing Machinery (ACM), 2019. pp. 1521-1531

BibTeX

@inproceedings{eb49feadbe26450a8f462850877c632c,
title = "Crowd-Mapping Urban Objects from Street-Level Imagery",
abstract = "Knowledge about the organization of the main physical elements (e.g. streets) and objects (e.g. trees) that structure cities is important in the maintenance of city infrastructure and the planning of future urban interventions. In this paper, a novel approach to crowd-mapping urban objects is proposed. Our method capitalizes on strategies for generating crowdsourced object annotations from street-level imagery, in combination with object density and geo-location estimation techniques to enable the enumeration and geo-tagging of urban objects. To address both the coverage and precision of the mapped objects within budget constraints, we design a scheduling strategy for micro-task prioritization, aggregation, and assignment to crowd workers. We experimentally demonstrate the feasibility of our approach through a use case pertaining to the mapping of street trees in New York City and Amsterdam. We show that anonymous crowds can achieve high recall (up to 80{\%}) and precision (up to 68{\%}), with geo-location precision of approximately 3m. We also show that similar performance could be achieved at city scale, possibly with stringent budget constraints.",
keywords = "Crowd-Mapping, Street-Level Imagery, Task Scheduling, Crowdsourcing, Urban Objects",
author = "Sihang Qiu and Achilleas Psyllidis and Alessandro Bozzon and Geert-Jan Houben",
year = "2019",
doi = "10.1145/3308558.3313651",
language = "English",
pages = "1521--1531",
booktitle = "Proceedings of the 2019 World Wide Web Conference",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS

TY - GEN

T1 - Crowd-Mapping Urban Objects from Street-Level Imagery

AU - Qiu, Sihang

AU - Psyllidis, Achilleas

AU - Bozzon, Alessandro

AU - Houben, Geert-Jan

PY - 2019

Y1 - 2019

N2 - Knowledge about the organization of the main physical elements (e.g. streets) and objects (e.g. trees) that structure cities is important in the maintenance of city infrastructure and the planning of future urban interventions. In this paper, a novel approach to crowd-mapping urban objects is proposed. Our method capitalizes on strategies for generating crowdsourced object annotations from street-level imagery, in combination with object density and geo-location estimation techniques to enable the enumeration and geo-tagging of urban objects. To address both the coverage and precision of the mapped objects within budget constraints, we design a scheduling strategy for micro-task prioritization, aggregation, and assignment to crowd workers. We experimentally demonstrate the feasibility of our approach through a use case pertaining to the mapping of street trees in New York City and Amsterdam. We show that anonymous crowds can achieve high recall (up to 80%) and precision (up to 68%), with geo-location precision of approximately 3m. We also show that similar performance could be achieved at city scale, possibly with stringent budget constraints.

AB - Knowledge about the organization of the main physical elements (e.g. streets) and objects (e.g. trees) that structure cities is important in the maintenance of city infrastructure and the planning of future urban interventions. In this paper, a novel approach to crowd-mapping urban objects is proposed. Our method capitalizes on strategies for generating crowdsourced object annotations from street-level imagery, in combination with object density and geo-location estimation techniques to enable the enumeration and geo-tagging of urban objects. To address both the coverage and precision of the mapped objects within budget constraints, we design a scheduling strategy for micro-task prioritization, aggregation, and assignment to crowd workers. We experimentally demonstrate the feasibility of our approach through a use case pertaining to the mapping of street trees in New York City and Amsterdam. We show that anonymous crowds can achieve high recall (up to 80%) and precision (up to 68%), with geo-location precision of approximately 3m. We also show that similar performance could be achieved at city scale, possibly with stringent budget constraints.

KW - Crowd-Mapping

KW - Street-Level Imagery

KW - Task Scheduling

KW - Crowdsourcing

KW - Urban Objects

U2 - 10.1145/3308558.3313651

DO - 10.1145/3308558.3313651

M3 - Conference contribution

SP - 1521

EP - 1531

BT - Proceedings of the 2019 World Wide Web Conference

PB - Association for Computing Machinery (ACM)

CY - New York, NY

ER -

ID: 51740999