Multipass Data Integration For Automatic Detection And Classification Of Objects

• US 20110103642A1
• Filed: 10/30/2009
• Published: 05/05/2011
• Est. Priority Date: 10/30/2009
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Applied Signal Technology Incorporated (Rtx Corporation)
• Inventors: Wilby, Andrew D., Harbaugh, J. Kent
• Granted Patent: US 8,275,172 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/253 of extracted features
• CPC Class Codes: G06V 2201/07 Target detection

Abstract

Classification of a potential target is accomplished by receiving image information, detecting a potential target within the image information and determining a plurality of features forming a feature set associated with the potential target. The location of the potential target is compared with a detection database to determine if it is close to an element in the detection database. If not, a single-pass classifier receives a potential target'"'"'s feature set, classifies the potential target, and transmits the location, feature set and classification to the detection database. If it is close, a fused multi-pass feature determiner determines fused multi-pass features of the potential target and a multi-pass classifier receives the potential target'"'"'s feature set and fused multi-pass features, classifies the potential target, and transmits its location, feature set, fused multi-pass features and classification to the detection database.

Claims

1. An apparatus comprising:

an input configured to receive image information;

a detector configured to detect a potential target within the image information and determine a plurality of features forming a feature set associated with the potential target, wherein detection is based upon at least some of the determined features and/or a location of the potential target;

a detection database configured to store at least location, features, fused multi-pass features and classification of potential targets;

a comparator configured to compare the location of a potential target with contents of the detection database to determine if the location of the potential target is close to the location of an element in the detection database;

a single-pass classifier configured to (a) receive a potential target'"'"'s feature set if the potential target is not close to the location of an element in the detection database, (b) classify the potential target, and (c) transmit the location, feature set and classification of the potential target to the detection database;

a fused multi-pass feature determiner configured to determine fused multi-pass features of the potential target if the potential target is close to the location of an element in the detection database; and

a multi-pass classifier configured to (a) receive the potential target'"'"'s feature set and fused multi-pass features if the potential target is close to the location of an element in the detection database, (b) classify the potential target, and (c) transmit the location, feature set, fused multi-pass features and classification of the potential target to the detection database.

2. A method, comprising:

receiving image information;

detecting a potential target within the image information and determining a plurality of features forming a feature set associated with the potential target, wherein the detecting is based upon at least some of the determined features and/or a location of the potential target;

comparing the location of a potential target with contents of a detection database to determine if the location of the potential target is close to the location of an element in the detection database;

using a single-pass classifier configured to (a) receive a potential target'"'"'s feature set if the potential target is not close to the location of an element in the detection database, (b) classify the potential target, and (c) transmit the location, feature set and classification of the potential target to the detection database;

using a fused multi-pass feature determiner configured to determine fused multi-pass features of the potential target if the potential target is close to the location of an element in the detection database; and

using a multi-pass classifier configured to (a) receive the potential target'"'"'s feature set and fused multi-pass features if the potential target is close to the location of an element in the detection database, (b) classify the potential target, and (c) transmit the location, feature set, fused multi-pass features and classification of the potential target to the detection database.

3. An apparatus, comprising:

means for receiving image information;

means for detecting a potential target within the image information and determining a plurality of features forming a feature set associated with the potential target, wherein the detecting is based upon at least some of the determined features and/or a location of the potential target;

detection database means configured to store at least location, features, fused multi-pass features and classification of potential targets;

means for comparing the location of a potential target with contents of the detection database means to determine if the location of the potential target is close to the location of an element in the detection database means;

a single-pass classifier means configured to (a) receive a potential target'"'"'s feature set if the potential target is not close to the location of an element in the detection database means, (b) classify the potential target, and (c) transmit the location, feature set and classification of the potential target to the detection database means;

a fused multi-pass feature determination means configured to determine fused multi-pass features of the potential target if the potential target is close to the location of an element in the detection database means; and

a multi-pass classifier means configured to (a) receive the potential target'"'"'s feature set and fused multi-pass features if the potential target is close to the location of an element in the detection database means, (b) classify the potential target, and (c) transmit the location, feature set, fused multi-pass features and classification of the potential target to the detection database means.