A Caltech Library Service

System and Method for Locating and Performing Fine Grained Classification from Multi-View Image Data

Perona, Pietro and Branson, Steven J. and Wegner, Jan D. and Hall, David C. (2017) System and Method for Locating and Performing Fine Grained Classification from Multi-View Image Data. Patent number: US20170287170A1.

[img] PDF (US20170287170A1) - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Some embodiments of the invention provide a method for identifying geographic locations and for performing a fine-grained classification of elements detected in images captured from multiple different viewpoints or perspectives. In several embodiments, the method identifies the geographic locations by probabilistically combining predictions from the different viewpoints by warping their outputs to a common geographic coordinate frame. The method of certain embodiments performs the fine-grained classification based on image portions from several images associated with a particular geographic location, where the images are captured from different perspectives and/or zoom levels.

Item Type:Patent
Patent Classification:Current U.S. Class: 1/1. Current CPC Class: G06T 7/97 20170101; G06K 9/00791 20130101; B60R 1/002 20130101; G06T 2207/10032 20130101; G05D 1/0088 20130101; B60R 2300/102 20130101; B60R 2300/301 20130101; B60R 2300/607 20130101; G06T 2207/20084 20130101. International Class: G06T 7/00 20060101 G06T007/00; B60R 1/00 20060101 B60R001/00; G06K 9/00 20060101 G06K009/00.
Patent Assignee:California Institute of Technology, ETH Zurich
Related URLs:
URLURL TypeDescription Patents Patent Office
Perona, Pietro0000-0002-7583-5809
Additional Information:Application filed: April 3, 2017. Application published: October 5, 2017.
Record Number:CaltechAUTHORS:20180622-124600364
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87332
Deposited By: Caroline Murphy
Deposited On:05 Jul 2018 23:03
Last Modified:03 Oct 2019 19:54

Repository Staff Only: item control page