Search

Quanfu B Fan

from Lexington, MA
Age ~52
Get Report
Also known as:
U Fan
Connected to:
Allison Fan, 29Bei Fan, 44Bobby H Fan, 55Bonnie P Fan, 33Brian W Fan, 61Caleb K Fan, 27Charles W Fan, 53Cheng G Fan, 60Chenming Fan, 40Chi R Fan, 67

Quanfu Fan Phones & Addresses

  • Lexington, MA
  • 162 Curtis St, Somerville, MA 02144
  • Yorktown Heights, NY
  • Elmsford, NY
  • 407 Santa Rita Ave, Tucson, AZ 85719
  • Tarrytown, NY
  • Medford, MA

Work

Company: Ibm Jan 2010 Address: Greater New York City Area Position: Research staff member

Education

Degree: MS & PHD School / High School: University of Arizona 2001 to 2008 Specialities: Computer Science

Skills

Computer Vision • Machine Learning • Data Mining • Computer Science • Algorithms • Artificial Intelligence • Pattern Recognition • Image Processing • Signal Processing • C++ • Software Engineering • Python • Latex • Java • Distributed Systems • C

Industries

Research

Resumes

Resumes

Quanfu Fan Photo 1

Research Staff Member

View page
Location:
Somerville, MA
Industry:
Research
Work:
IBM - Greater New York City Area since Jan 2010
Research Staff Member
IBM Mar 2008 - Dec 2009
PostDoc
Education:
University of Arizona 2001 - 2008
MS & PHD, Computer Science
Skills:
Computer Vision
Machine Learning
Data Mining
Computer Science
Algorithms
Artificial Intelligence
Pattern Recognition
Image Processing
Signal Processing
C++
Software Engineering
Python
Latex
Java
Distributed Systems
C

Publications

Us Patents

Analyzing Repetitive Sequential Events

View page
US Patent:
8165349, Apr 24, 2012
Filed:
Nov 29, 2008
Appl. No.:
12/325176
Inventors:
Russell Patrick Bobbitt - Pleasantville NY, US
Quanfu Fan - Somerville MA, US
Arun Hampapur - Norwalk CT, US
Frederik Kjeldsen - Poughkeepsie NY, US
Sharathchandra Umapathirao Pankanti - Darien CT, US
Akira Yanagawa - New York NY, US
Yun Zhai - White Plains NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06K 9/00
H04W 4/00
US Classification:
382103, 382291, 370328
Abstract:
Techniques for analyzing one or more sequential events performed by a human actor to evaluate efficiency of the human actor are provided. The techniques include identifying one or more segments in a video sequence as one or more components of one or more sequential events performed by a human actor, integrating the one or more components into one or more sequential events by incorporating a spatiotemporal model and one or more event detectors, and analyzing the one or more sequential events to analyze behavior of the human actor.

Location-Aware Event Detection

View page
US Patent:
8253831, Aug 28, 2012
Filed:
Nov 29, 2008
Appl. No.:
12/325178
Inventors:
Russell Patrick Bobbitt - Pleasantville NY, US
Quanfu Fan - Somerville MA, US
Arun Hampapur - Norwalk CT, US
Frederik Kjeldsen - Poughkeepsie NY, US
Sharathchandra Umapathirao Pankanti - Darien CT, US
Akira Yanagawa - New York NY, US
Yun Zhai - White Plains NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
H04N 9/083
US Classification:
348274, 348150
Abstract:
Techniques for detecting one or more events are provided. The techniques include using one or more regions of interest on a video sequence to cover a location for one or more events, wherein each event is associated with at least one of the one or more regions of interest, applying multiple-instance learning to the video sequence to construct one or more location-aware event models, and applying the models to the video sequence to determine the one or more regions of interest that are associated with the one or more events.

Optimizing Video Stream Processing

View page
US Patent:
8259175, Sep 4, 2012
Filed:
Feb 1, 2010
Appl. No.:
12/697530
Inventors:
Russell Patrick Bobbitt - Pleasantvile NY, US
Quanfu Fan - Somerville MA, US
Sachiko Miyazawa - Bronx NY, US
Sharathchandra Umapathirao Pankanti - Darien CT, US
Yun Zhai - Mount Kisco NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
H04N 7/18
US Classification:
348150, 382100, 709219, 709231, 709232, 706 47, 706 52
Abstract:
The present invention involves implementation of an intelligent switching program, whereby the processing power required to monitor check-out stations is considerably reduced. The present invention monitors a subset of check-out stations at any given time, instead of monitoring all check-out stations at all times. The subset of check-out stations is determined dynamically according to, but not limited to, cashier records, input parameters from the user, current lane activity, past lane activity, time of day, etc. Statistical models (e. g. , effective population sampling and/or population hypothesis tests) are developed along these lines that guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled. By monitoring fewer check-out stations, while maintaining target performance accuracy, the amount of data that end users must deal with is significantly reduced.

Automatically Calibrating Regions Of Interest For Video Surveillance

View page
US Patent:
8345101, Jan 1, 2013
Filed:
Oct 31, 2008
Appl. No.:
12/262446
Inventors:
Russell Patrick Bobbitt - Pleasantville NY, US
Quanfu Fan - Somerville MA, US
Arun Hampapur - Norwalk CT, US
Frederik Kjeldsen - Poughkeepsie NY, US
Sharathchandra Umapathirao Pankanti - Darien CT, US
Akira Yanagawa - New York NY, US
Yun Zhai - White Plains NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
H04N 7/18
US Classification:
348150, 348143, 348169
Abstract:
Techniques for automatically calibrating one or more regions of interest for video surveillance are provided. The techniques include at a user-defined frequency, determining if one or more regions of interest (ROIs) are present within a field of view of a camera, if one or more ROIs are present within the field of view of the camera, automatically calibrating the one or more ROIs within the field of view of the camera, and if one or more ROIs are not present within the field of view of the camera, sending an alert to a user.

Generating An Alert Based On Absence Of A Given Person In A Transaction

View page
US Patent:
8429016, Apr 23, 2013
Filed:
Oct 31, 2008
Appl. No.:
12/262454
Inventors:
Russell Patrick Bobbitt - Pleasantville NY, US
Quanfu Fan - Somerville MA, US
Arun Hampapur - Norwalk CT, US
Frederik Kjeldsen - Poughkeepsie NY, US
Sharathchandra Umapathirao Pankanti - Darien CT, US
Akira Yanagawa - New York NY, US
Yun Zhai - White Plains NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06Q 20/00
US Classification:
705 16, 705 18
Abstract:
Techniques for generating an alert based on absence of a given person in a transaction are provided. The techniques include monitoring, via video, a transaction, wherein the transaction includes presence of a given person in the transaction, relating the video of the transaction to a corresponding portion of a transaction log (TLOG), using the video and corresponding portion of the TLOG to detect if the given person in the transaction is present, and generating an alert if the given person is not present at the transaction.

Optimization Of Human Activity Determination From Video

View page
US Patent:
8478048, Jul 2, 2013
Filed:
Jul 8, 2010
Appl. No.:
12/832379
Inventors:
Lei Ding - Hawthorne NY, US
Quanfu Fan - Hawthorne NY, US
Sharathchandra U. Pankanti - Hawthorne NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06K 9/46
G06K 9/00
US Classification:
382190, 382100
Abstract:
In an embodiment, automated analysis of video data for determination of human behavior includes providing a programmable device that segments a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The optimized visual event is processed in view of associated non-video transaction data and the binary variable by associating the optimized visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the optimized visual event is not associable with the logged transaction, and dropping the optimized visual event if the binary variable is false and the optimized visual event is not associable.

Dynamically Learning Attributes Of A Point Of Sale Operator

View page
US Patent:
8494214, Jul 23, 2013
Filed:
Oct 30, 2008
Appl. No.:
12/261304
Inventors:
Russell P. Bobbitt - Pleasantville NY, US
Quanfu Fan - Somerville MA, US
Arun Hampapur - Norwalk CT, US
Frederik C. M. Kjeldsen - Poughkeepsie NY, US
Sharathchandra U. Pankanti - Darien CT, US
Akira Yanagawa - New York NY, US
Yun Zhai - White Plains NY, US
Assignee:
Toshiba Global Commerce Solutions Holdings Corporation - Tokyo
International Classification:
G06K 9/00
US Classification:
382103
Abstract:
An approach that dynamically learns a set of attributes of an operator of a point of sale (POS) is provided. In one embodiment, there is an attribute tool, including an extraction component configured to receive sensor data of a set of moving objects, and extract a set of attributes from each of the set of moving objects captured within the scan area at the POS; an identification component configured to update an appearance model with the set of attributes from each of the set of moving objects; and an analysis component configured to analyze the appearance model to identify at least one of the set of moving objects as an operator of the POS.

Sequential Event Detection From Video

View page
US Patent:
8548203, Oct 1, 2013
Filed:
Jul 12, 2010
Appl. No.:
12/834104
Inventors:
Russell P. Bobbitt - Hawthorne NY, US
Lei Ding - Hawthorne NY, US
Quanfu Fan - Hawthorne NY, US
Sachiko Miyazawa - Hawthorne NY, US
Sharathchandra U. Pankanti - Hawthorne NY, US
Yun Zhai - Hawthorne NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06K 9/00
G06K 9/48
US Classification:
382107, 382199
Abstract:
Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.
Control profile
Quanfu B Fan from Lexington, MA, age ~52 Get Report