Varsha C Hedau

US Patent:

20130147798, Jun 13, 2013

Filed:

Dec 8, 2011

Appl. No.:

13/314723

Inventors:

Kevin Karsch - Urbana IL, US
Varsha Chandrashekhar Hedau - Sunnyvale CA, US
David A. Forsyth - Urbana IL, US
Derek Hoiem - Champaign IL, US

Assignee:

The Board of Trustees of the University of Illinois - Urbana IL

International Classification:

G06T 17/00

US Classification:

345420

Abstract:

An image into which one or more objects are to be inserted is obtained. Based on the image, both a 3-dimensional (3D) representation and a light model of the scene in the image are generated. One or more objects are added to the 3D representation of the scene. The 3D representation of the scene is rendered, based on the light model, to generate a modified image that is the obtained image modified to include the one or more objects.

US Patent:

20120321175, Dec 20, 2012

Filed:

Jun 17, 2011

Appl. No.:

13/162591

Inventors:

Varsha Hedau - Schaumburg IL, US
Sudipta Sinha - Redmond WA, US
Charles Lawrence Zitnick - Seattle WA, US
Richard Szeliski - Bellevue WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/62

US Classification:

382159, 382224

Abstract:

A mobile device having the capability of performing real-time location recognition with assistance from a server is provided. The approximate geophysical location of the mobile device is uploaded to the server. Based on the mobile device's approximate geophysical location, the server responds by sending the mobile device a message comprising a classifier and a set of feature descriptors. This can occur before an image is captured for visual querying. The classifier and feature descriptors are computed during an offline training stage using techniques to minimize computation at query time. The classifier and feature descriptors are used to perform visual recognition in real-time by performing the classification on the mobile device itself.

US Patent:

20190258861, Aug 22, 2019

Filed:

Apr 30, 2019

Appl. No.:

16/399507

Inventors:

- San Francisco CA, US
Vasudev Parameswaran - Fremont CA, US
Thommen Korah - San Ramon CA, US
Varsha Hedau - San Jose CA, US
Radek Grzeszczuk - Menlo Park CA, US
Yanxi Liu - Mountain View CA, US

International Classification:

G06K 9/00
G06K 9/46
G06T 7/90
G06K 9/62

Abstract:

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

US Patent:

20180060664, Mar 1, 2018

Filed:

Oct 23, 2017

Appl. No.:

15/790571

Inventors:

- San Francisco CA, US
Vasudev Parameswaran - Fremont CA, US
Thommen Korah - San Ramon CA, US
Varsha Hedau - San Jose CA, US
Radek Grzeszczuk - Menlo Park CA, US
Yanxi Liu - Mountain View CA, US

International Classification:

G06K 9/00
G06K 9/46
G06K 9/62

Abstract:

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

US Patent:

20170091553, Mar 30, 2017

Filed:

Dec 8, 2016

Appl. No.:

15/373354

Inventors:

- San Francisco CA, US
Vasudev Parameswaran - Fremont CA, US
Thommen Korah - San Ramon CA, US
Varsha Hedau - San Jose CA, US
Radek Grzeszczuk - Menlo Park CA, US
Yanxi Liu - Mountain View CA, US

International Classification:

G06K 9/00
G06K 9/46
G06K 9/62

Abstract:

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

US Patent:

20150356368, Dec 10, 2015

Filed:

Jun 8, 2014

Appl. No.:

14/298932

Inventors:

- Redmond WA, US
Vasudev Parameswaran - Fremont CA, US
Thommen Korah - San Ramon CA, US
Varsha Hedau - San Jose CA, US
Radek Grzeszczuk - Menlo Park CA, US
Yanxi Liu - Mountain View CA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06K 9/46
G06T 7/40
G06K 9/62

Abstract:

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.