James R Vaughan

US Patent:

8411086, Apr 2, 2013

Filed:

Feb 24, 2009

Appl. No.:

12/392056

Inventors:

Eleanor Rieffel - Mountain View CA, US
Donald Kimber - Foster City CA, US
Jun Shingu - San Jose CA, US
Chong Chen - Chicago IL, US
James Vaughan - Sunnyvale CA, US
Sagar Gattepally - Fremont CA, US

Assignee:

Fuji Xerox Co., Ltd. - Tokyo

International Classification:

G06T 15/00
G06T 17/00
G06K 9/00

US Classification:

345420, 345419, 382154

Abstract:

A method and system for defining a model by analyzing images of a physical space. In some embodiments the images of a physical space contain distinctive visual features with associated semantic information, and the model is defined using image feature detection techniques to identify distinctive visual features and a rich marker-based markup language to give meaning to the distinctive visual features. In some embodiments the distinctive visual features are predefined markers, and the markup language specifies model aspects and rules for combining semantic information from a plurality of markers to define the model.

US Patent:

20090002489, Jan 1, 2009

Filed:

Jun 29, 2007

Appl. No.:

11/771626

Inventors:

Tao Yang - Xi'an, CN
Francine Chen - Menlo Park CA, US
Donald G. Kimber - Foster City CA, US
Xuemin Liu - Sunnyvale CA, US
James Vaughan - Sunnyvale CA, US

Assignee:

FUJI XEROX CO., LTD. - Tokyo

International Classification:

H04N 7/18
G06K 9/62

US Classification:

348143, 382103, 348E07085

Abstract:

Visual tracking of multiple objects in a crowded scene is critical for many applications include surveillance, video conference and human computer interaction. Complex interactions between objects result in partial or significant occlusions, making tracking a highly challenging problem. Presented is a novel efficient approach to tracking a varying number of objects through occlusion. The object tracking during occlusion is posed as a track-based segmentation problem in the joint-object space. Appearance models are used to interpret the foreground into multiple layer probabilistic masks in a Bayesian framework. The search for optimal segmentation solution is achieved by a greedy searching algorithm and integral image for real-time computing. Promising results on several challenging video surveillance sequences have been demonstrated.

US Patent:

20110279697, Nov 17, 2011

Filed:

May 12, 2010

Appl. No.:

12/779021

Inventors:

Jun SHINGU - Kanagawa, JP
Donald Kimber - Foster City CA, US
Eleanor Rieffel - Mountain View CA, US
James Vaughan - Sunnyvale CA, US
Kathleen Tuite - Seattle WA, US

Assignee:

FUJI XEROX CO., LTD. - Minato-ku

International Classification:

H04N 5/222

US Classification:

3482221, 348E05022

Abstract:

Systems and methods for repeat photography and difference extraction that help users take pictures from the same position and camera angle as earlier photos. The system automatically extracts differences between the photos. Camera poses are estimated and then indicators are rendered to show the desired camera angle, which guide the user to the same camera angle for repeat photography. Using 3D rendering techniques, photos are virtually projected onto a 3D model to adjust them and improve the match between the photos, and the difference between the two photos are detected and highlighted. Highlighting the detected differences helps users to notice the differences.

US Patent:

48005908, Jan 24, 1989

Filed:

Jan 14, 1985

Appl. No.:

6/691225

Inventors:

James C. Vaughan - Palo Alto CA

International Classification:

H04K 100
G07P 700

US Classification:

380 25

Abstract:

A computer access system includes a password generator (10) and an lock computer (50) connected to receive passwords generated by the password generator and grant access to a host computer (52) when a password from the password generator (10) matches a password separately generated by the lock computer (50). The password generator (10) and the lock computer (50) have corresponding pseudo-random number sequences stored in memories (26 and 90). The password generator (10) and the lock computer (50) have synchronized clocks (30 and 84), which define time intervals. During a given time interval, entry of a personal identification number in password generator (10) will cause the password generator (10) to generate a unique password from the random number sequence in memory (26) and time interval information from clock (30). The user transmits the so-generated password to the lock computer (50), which independently generates a comparison password from the corresponding pseudo-random number sequence stored in memory (90), and the time interval defined by clock (84). If the passwords match, access to computer (52) is granted by the lock computer (50).

US Patent:

20140152660, Jun 5, 2014

Filed:

Dec 4, 2012

Appl. No.:

13/705013

Inventors:

- Tokyo, JP
Donald KIMBER - Foster City CA, US
James VAUGHAN - Mountain View CA, US

Assignee:

FUJI XEROX CO., LTD. - Tokyo

International Classification:

G06T 17/10

US Classification:

345420

Abstract:

A method of creating a 3-D model by capturing partial 3-D models each comprising a sequence of 2-D images, analyzing each of the partial 3-D models to identify image features in the sequence of 2-D images of each of the partial 3-D models, identifying pairs of overlapping image features between the 2-D mages of each of the partial 3-D models by identifying image features in each 2-D image in the sequence of 2-D images of each of the partial 3-D models that overlaps image features in 2-D images of the sequence of 2-D images of the other partial 3-D models and selecting a 2-d image from each of the partial 3-D models, computing an initial transformation between 3-D coordinates of individual pairs of identified image features between the selected 2-D image from each of the partial 3-D models; and generating a final 3-D model based on the initial transformation.