Advanced search
Start date
Betweenand


Multi-label Building Functions Classification from Ground Pictures using Convolutional Neural Networks

Full text
Author(s):
Srivastava, Shivangi ; Vargas-Munoz, John E. ; Swinkels, David ; Tuia, Devis ; Hu, Y ; Gao, S ; Newsam, S ; Lunga, D
Total Authors: 8
Document type: Journal article
Source: PROCEEDINGS OF THE 2ND ACM SIGSPATIAL INTERNATIONAL WORKSHOP ON AI FOR GEOGRAPHIC KNOWLEDGE DISCOVERY (GEOAI 2018); v. N/A, p. 4-pg., 2018-01-01.
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 multi-label 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. (AU)

FAPESP's process: 17/10086-0 - Interactive rural building detection and delineation using remote sensing images
Grantee:John Edgar Vargas Muñoz
Support Opportunities: Scholarships abroad - Research Internship - Doctorate