SYSTEMS AND METHODS FOR EFFICIENTLY AND ACCURATELY DETECTING CHANGES IN SPATIAL FEATURE DATA

• US 20130156307A1
• Filed: 12/16/2011
• Published: 06/20/2013
• Est. Priority Date: 12/16/2011
• Status: Active Grant

• Current Assignee: Ollnova Technologies Limited (Atlantic IP Services Limited)
• Original Assignee: Harris Corporation (L3Harris Technologies, Inc.)
• Inventors: Yates, J. Harlan, McGonagle, Michael, Rahmes, Mark, Haden, Robert
• Granted Patent: US 8,855,427 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 10/757 Matching configurations of points or features
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes

Abstract

Systems (100) and methods (300) for efficiently and accurately detecting changes in feature data. The methods generally involve: determining first vectors for first features extracted from a first image using pixel information associated therewith; comparing the first vectors with second vectors defined by spatial feature data; classifying the first features into a plurality of classes based on the results of the vector comparisons; and analyzing the first image to determine if any one of the first features of at least one of the plurality of classes indicates that a relevant change has occurred in relation to an object represented thereby.

Claims

1. A method for efficiently and accurately detecting changes in feature data, comprising:

determining, by at least one electronic circuit, first vectors for first features extracted from a first image;

comparing, by the electronic circuit, the first vectors with pre-defined second vectors;

classifying, by the electronic circuit, the first features into a plurality of classes based on the results of the comparing step; and

analyzing the first image to determine if any one of the first features of at least one of the plurality of classes indicates that a relevant change has occurred in relation to an object represented thereby.

2. The method according to claim 1, wherein the first vectors are determined by converting locations of pixels defining the first features to coordinates of a multi-dimensional space.

3. The method according to claim 1, wherein the first vectors and the second vectors are compared with each other to determine mathematically which of the first features overlap one or more of second features.

4. The method according to claim 3, wherein the first features which overlap the second features are classified as “

matched features”

.

5. The method according to claim 3, wherein the first features which do not overlap any of the second features are classified as “

new features”

.

6. The method according to claim 3, wherein the second features which do not have any overlapping first features are classified as “

deleted features”

.

7. The method according to claim 1, further comprising determining, by the electronic circuit, a plurality of confidence values indicating a degree of similarity, difference or overlap between the first features and pre-defined second features.

8. The method according to claim 1, wherein the analyzing step comprises:

automatically and simultaneously generating a plurality of chip images for the first image, the chip images comprising panned and/or zoomed views of the first image of objects defined by a user-selected feature and other features of the same feature class as the user-selected feature; and

analyzing the plurality of chip images to determine if any one of the first features indicates that a relevant change has occurred in relation to the object represented thereby.

9. The method according to claim 1, wherein the analyzing step comprises comparing the contents of the first image with the contents of a second image to determine if any one of the first features indicates that a relevant change has occurred in relation to the object represented thereby.

10. The method according to claim 1, wherein the analyzing step comprises:

generating at least one color difference image using imagery data for the first image and imagery data for a second image; and

analyzing the color difference image to determine if any one of the features thereof indicates that a relevant change has occurred in relation to the object represented thereby.

11. A system, comprising:

at least one electronic circuit configured to

determine first vectors for first features extracted from a first image,

compare the first vectors with pre-defined second vectors,

classify the first features into a plurality of classes based on the results of the comparing step, and

analyze the first image to determine if any one of the first features of at least one of the plurality of classes indicates that a relevant change has occurred in relation to an object represented thereby.

12. The system according to claim 11, wherein the first vectors are determined by converting locations of pixels defining the first features to coordinates of a multi-dimensional space.

13. The system according to claim 11, wherein the first vectors and the second vectors are compared with each other to determine mathematically which of the first features overlap one or more second features defined by previously stored data.

14. The system according to claim 13, wherein the first features which overlap the second features are classified as “

matched features”

.

15. The system according to claim 13, wherein the first features which do not overlap any of the second features are classified as “

new features”

.

16. The system according to claim 13, wherein the second features which do not have any overlapping first features are classified as “

deleted features”

.

17. The system according to claim 11, wherein the electronic circuit is further configured to determine a plurality of confidence values indicating a degree of similarity, difference or overlap between the first features and second features defined by previously stored data.

18. The system according to claim 11, wherein the electronic circuit is further configured to

automatically and simultaneously generate a plurality of chip images for the first image, the chip images comprising panned and/or zoomed views of the first image of objects defined by a user-selected feature and other features of the same feature class as the user-selected feature, and

facilitate a user analysis of the plurality of chip images to identify at least one first feature which indicates that a relevant change has occurred in relation to the object represented thereby.

19. The system according to claim 11, wherein the electronic circuit is further configured to facilitate a user comparison of the contents of the first image with the contents of a second image to identify at least one first feature which indicates that a relevant change has occurred in relation to the object represented thereby.

20. The system according to claim 11, wherein the electronic circuit is further configured to

generate at least one color difference image using imagery data for the first image and imagery data for a second image, and

facilitate a user analysis of the color difference image to identify at least one feature thereof which indicates that a relevant change has occurred in relation to the object represented thereby.