Detecting, classifying, and mapping retail storefronts using street-level imagery

Conference paper (2020)

Authors

S. Sharifi Noorian Web Information Systems - EEMCS
S. Qiu Web Information Systems - EEMCS
A. Bozzon Web Information Systems - EEMCS , Human-Centred Artificial Intelligence - IDE
G.J.P.M. Houben Web Information Systems - EEMCS
Research Group
Web Information Systems (EEMCS) (TU Delft)
Copyright: © 2020 S. Sharifi Noorian, S. Qiu, A. Psyllidis, A. Bozzon, G.J.P.M. Houben
DOI: https://doi.org/10.1145/3372278.3390706
More Info
expand_more

Published Date

2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Software Technology

Research Group

Web Information Systems

Abstract

Up-to-date listings of retail stores and related building functions are challenging and costly to maintain. We introduce a novel method for automatically detecting, geo-locating, and classifying retail stores and related commercial functions, on the basis of storefronts extracted from street-level imagery. Specifically, we present a deep learning approach that takes storefronts from street-level imagery as input, and directly provides the geo-location and type of commercial function as output. Our method showed a recall of 89.05% and a precision of 88.22% on a real-world dataset of street-level images, which experimentally demonstrated that our approach achieves human-level accuracy while having a remarkable run-time efficiency compared to methods such as Faster Region-Convolutional Neural Networks (Faster R-CNN) and Single Shot Detector (SSD).

Files

3372278.3390706.pdf
(.pdf | 2.44 Mb)
- Embargo expired in 01-01-2021