Gang Chang Xu

US Patent:

6529495, Mar 4, 2003

Filed:

May 24, 1999

Appl. No.:

09/317333

Inventors:

Joseph R. Cavallaro - Pearland TX
Gang Xu - Houston TX

Assignee:

Nokia Telecommunications, Oy

International Classification:

H04B 7216

US Classification:

370342, 375148, 375150

Abstract:

A multistage detector is disclosed that maximizes computation power while minimizing system delay. The differencing multistage detector receives signals from a plurality of users in a cell of a communications system and reduces the effect of multiple access interference to a signal from a desired user caused by interference from other users in the cell. The differencing multistage detector includes a plurality of stages, each stage including an interference canceller for removing intra-cell interference caused by the other users in the cell and producing an estimation output vector, wherein except for a first stage, the estimation output vector of a current stage is based on both a decision of the interference canceller of the current stage and the output from an interference canceller of a previous stage. The estimation output vector of a current stage is produced by combining the output from an interference canceller of a previous stage and the decision of the interference canceller of the current stage. Except for the first stage each interference canceller calculates an estimate of multi-user interference by computing a product of a cross-correlation of the received signals and a difference signal thereby reducing the number of multiplication operations required.

US Patent:

7843378, Nov 30, 2010

Filed:

Mar 4, 2008

Appl. No.:

12/074511

Inventors:

Chandrasekaran Venkatachalam - Fort Collins CO, US
Gang Xu - Houston TX, US
Yanting Wang - Aurora CO, US

Assignee:

Colorado State University Research Foundation - Fort Collins CO

International Classification:

G01S 13/95

US Classification:

342 26R, 342 26 D, 342196

Abstract:

Methods and systems for estimating atmospheric conditions are disclosed according to embodiments of the invention. In one embodiment, a method may include receiving reflective atmospheric data and solving a flow equation for motion coefficients using the reflective atmospheric data. Future atmospheric conditions can be estimated using the motion coefficients and the reflective atmospheric data. In another embodiment of the invention, the flow equation is solved in the frequency domain. Various linear regression tools may be used to solve for the coefficients. In another embodiment of the system, a radar system is disclosed that predicts future atmospheric conditions by solving the spectral flow equation.

US Patent:

8121968, Feb 21, 2012

Filed:

Sep 11, 2008

Appl. No.:

12/208551

Inventors:

John Eric Eaton - Houston TX, US
Wesley Kenneth Cobb - The Woodlands TX, US
Ming-Jung Seow - Houston TX, US
David Samuel Friedlander - Houston TX, US
Gang Xu - Houston TX, US

Assignee:

Behavioral Recognition Systems, Inc. - Houston TX

International Classification:

G06F 17/00
G06F 15/18
G06N 5/02
G06K 9/62
G06K 9/46
G06K 9/66

US Classification:

706 46, 706 12, 382155, 382192, 382227

Abstract:

A long-term memory used to store and retrieve information learned while a video analysis system observes a stream of video frames is disclosed. The long-term memory provides a memory with a capacity that grows in size gracefully, as events are observed over time. Additionally, the long-term memory may encode events, represented by sub-graphs of a neural network. Further, rather than predefining a number of patterns recognized and manipulated by the long-term memory, embodiments of the invention provide a long-term memory where the size of a feature dimension (used to determine the similarity between different observed events) may grow dynamically as necessary, depending on the actual events observed in a sequence of video frames.

US Patent:

8126833, Feb 28, 2012

Filed:

Dec 16, 2008

Appl. No.:

12/336354

Inventors:

Wesley Kenneth Cobb - The Woodlands TX, US
Ming-Jung Seow - Houston TX, US
Gang Xu - Houston TX, US

Assignee:

Behavioral Recognition Systems, Inc. - Houston TX

International Classification:

G06F 17/00
G06F 15/18
G06N 5/02
G06K 9/62
G06K 9/46
G06K 9/66

US Classification:

706 46, 706 12, 382155, 382192, 382227

Abstract:

Techniques are described for detecting anomalous events using a long-term memory in a video analysis system. The long-term memory may be used to store and retrieve information learned while a video analysis system observes a stream of video frames depicting a given scene. Further, the long-term memory may be configured to detect the occurrence of anomalous events, relative to observations of other events that have occurred in the scene over time. A distance measure may used to determine a distance between an active percept (encoding an observed event depicted in the stream of video frames) and a retrieved percept (encoding a memory of previously observed events in the long-term memory). If the distance exceeds a specified threshold, the long-term memory may publish the occurrence of an anomalous event for review by users of the system.

US Patent:

8131012, Mar 6, 2012

Filed:

Feb 8, 2008

Appl. No.:

12/028484

Inventors:

John Eric Eaton - Houston TX, US
Wesley Kenneth Cobb - Woodlands TX, US
Dennis Gene Urech - Katy TX, US
Bobby Ernest Blythe - Houston TX, US
David Samuel Friedlander - Houston TX, US
Rajkiran Kumar Gottumukkal - Houston TX, US
Lon William Risinger - Katy TX, US
Kishor Adinath Saitwal - Houston TX, US
Ming-Jung Seow - Houston TX, US
David Marvin Solum - Houston TX, US
Gang Xu - Houston TX, US
Tao Yang - Houston TX, US

Assignee:

BEHAVIORAL RECOGNITION SYSTEMS, Inc. - Houston TX

International Classification:

G06K 9/00

US Classification:

382103, 382155, 3405731

Abstract:

Embodiments of the present invention provide a method and a system for analyzing and learning behavior based on an acquired stream of video frames. Objects depicted in the stream are determined based on an analysis of the video frames. Each object may have a corresponding search model used to track an object's motion frame-to-frame. Classes of the objects are determined and semantic representations of the objects are generated. The semantic representations are used to determine objects' behaviors and to learn about behaviors occurring in an environment depicted by the acquired video streams. This way, the system learns rapidly and in real-time normal and abnormal behaviors for any environment by analyzing movements or activities or absence of such in the environment and identifies and predicts abnormal and suspicious behavior based on what has been learned.

US Patent:

8170283, May 1, 2012

Filed:

Sep 17, 2009

Appl. No.:

12/561977

Inventors:

Wesley Kenneth Cobb - The Woodlands TX, US
David Friedlander - Houston TX, US
Kishor Adinath Saitwal - Houston TX, US
Ming-Jung Seow - Houston TX, US
Gang Xu - Katy TX, US

Assignee:

Behavioral Recognition Systems Inc. - Houston TX

International Classification:

G06K 9/00
G08G 5/00

US Classification:

382103, 382291, 340948

Abstract:

Techniques are disclosed for a video surveillance system to learn to recognize complex behaviors by analyzing pixel data using alternating layers of clustering and sequencing. A video surveillance system may be configured to observe a scene (as depicted in a sequence of video frames) and, over time, develop hierarchies of concepts including classes of objects, actions and behaviors. That is, the video surveillance system may develop models at progressively more complex levels of abstraction used to identify what events and behaviors are common and which are unusual. When the models have matured, the video surveillance system issues alerts on unusual events.

US Patent:

8180105, May 15, 2012

Filed:

Sep 17, 2009

Appl. No.:

12/561956

Inventors:

Wesley Kenneth Cobb - The Woodlands TX, US
David Friedlander - Houston TX, US
Kishor Adinath Saitwal - Houston TX, US
Ming-Jung Seow - Houston TX, US
Gang Xu - Katy TX, US

Assignee:

Behavioral Recognition Systems, Inc. - Houston TX

International Classification:

G06K 9/00
G08G 5/00

US Classification:

382103, 382286, 340948

Abstract:

Techniques are disclosed for a video surveillance system to learn to recognize complex behaviors by analyzing pixel data using alternating layers of clustering and sequencing. A combination of a self organizing map (SOM) and an adaptive resonance theory (ART) network may be used to identify a variety of different anomalous inputs at each cluster layer. As progressively higher layers of the cortex model component represent progressively higher levels of abstraction, anomalies occurring in the higher levels of the cortex model represent observations of behavioral anomalies corresponding to progressively complex patterns of behavior.

US Patent:

8189905, May 29, 2012

Filed:

Jul 9, 2008

Appl. No.:

12/170283

Inventors:

John Eric Eaton - Houston TX, US
Wesley Kenneth Cobb - Woodlands TX, US
Dennis G. Urech - Katy TX, US
David S. Friedlander - Houston TX, US
Gang Xu - Houston TX, US
Ming-Jung Seow - Houston TX, US
Lon W. Risinger - Katy TX, US
David M. Solum - Houston TX, US
Tao Yang - Katy TX, US
Rajkiran K. Gottumukkal - Houston TX, US
Kishor Adinath Saitwal - Houston TX, US

Assignee:

Behavioral Recognition Systems, Inc. - Houston TX

International Classification:

G06K 9/62
G06K 9/00

US Classification:

382159, 382107

Abstract:

A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.