A Caltech Library Service

Cataloging Public Objects Using Aerial and Street-Level Images – Urban Trees

Wegner, Jan D. and Branson, Steve and Hall, David and Schindler, Konrad and Perona, Pietro (2016) Cataloging Public Objects Using Aerial and Street-Level Images – Urban Trees. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society Conference Publishing Services , Piscataway, NJ, pp. 6014-6023. ISBN 9781467388511.

[img] PDF (Author's copy. Includes supplemental material) - Accepted Version
See Usage Policy.

[img] PDF - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


Each corner of the inhabited world is imaged from multiple viewpoints with increasing frequency. Online map services like Google Maps or Here Maps provide direct access to huge amounts of densely sampled, georeferenced images from street view and aerial perspective. There is an opportunity to design computer vision systems that will help us search, catalog and monitor public infrastructure, buildings and artifacts. We explore the architecture and feasibility of such a system. The main technical challenge is combining test time information from multiple views of each geographic location (e.g., aerial and street views). We implement two modules: det2geo, which detects the set of locations of objects belonging to a given category, and geo2cat, which computes the fine-grained category of the object at a given location. We introduce a solution that adapts state-of-the-art CNN-based object detectors and classifiers. We test our method on “Pasadena Urban Trees”, a new dataset of 80,000 trees with geographic and species annotations, and show that combining multiple views significantly improves both tree detection and tree species classification, rivaling human performance.

Item Type:Book Section
Related URLs:
URLURL TypeDescription paper website
Perona, Pietro0000-0002-7583-5809
Additional Information:Copyright © 2016 IEEE. by The Institute of Electrical and Electronics Engineers, Inc. All rights reserved. Acknowledgements: We would like to thank Danny Carmichael, Jennifer Pope, Peter Marx, Ken Hudnut, Greg McPherson, Natalie Van Doorn, Emily Spillett, Jack Mc-Cabe, Vince Mikulanis, and Deborah Sheeler for their guidance and help providing training data. This work was supported by a gift from Google, and SNSF International Short Visit grant 162330.
Funding AgencyGrant Number
SNSF International Short Visit162330
Record Number:CaltechAUTHORS:20160914-111706205
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:70346
Deposited By: Katherine Johnson
Deposited On:14 Sep 2016 18:54
Last Modified:11 Nov 2021 04:27

Repository Staff Only: item control page