08270733 is referenced by 5 patents and cites 44 patents.

Techniques are disclosed for identifying anomaly object types during classification of foreground objects extracted from image data. A self-organizing map and adaptive resonance theory (SOM-ART) network is used to discover object type clusters and classify objects depicted in the image data based on pixel-level micro-features that are extracted from the image data. Importantly, the discovery of the object type clusters is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. The SOM-ART network is adaptive and able to learn while discovering the object type clusters and classifying objects and identifying anomaly object types.

Title
Identifying anomalous object types during classification
Application Number
12/551276
Publication Number
8270733 (B2)
Application Date
August 31, 2009
Publication Date
September 18, 2012
Inventor
Gang Xu
Katy
TX, US
Ming Jung Seow
Houston
TX, US
Rajkiran Kumar Gottumukkal
Houston
TN, US
David Friedlander
Houston
TX, US
Wesley Kenneth Cobb
The Woodlands
TX, US
Agent
Patterson & Sheridan
Assignee
Behavioral Recognition Systems
TX, US
IPC
G01V 3/00
G06K 9/62
View Original Source