Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published 2016 | Supplemental Material + Accepted Version
Book Section - Chapter Open

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

Abstract

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.

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.

Attached Files

Accepted Version - CVPR2016-WegnerBransonEtAl.pdf

Supplemental Material - S26-27-supp.pdf

Files

CVPR2016-WegnerBransonEtAl.pdf
Files (34.1 MB)
Name Size Download all
md5:c470cbcd7216089f02a21aa2acdf7537
22.1 MB Preview Download
md5:c9e77786f33862911935858b41e95855
11.9 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 20, 2023