IDENTIFYING GEOGRAPHIC-AREAS BASED ON CHANGE PATTERNS DETECTED FROM HIGH-RESOLUTION, REMOTELY SENSED IMAGERY

• US 20100100539A1
• Filed: 10/20/2008
• Published: 04/22/2010
• Est. Priority Date: 10/16/2008
• Status: Active Grant

• Current Assignee: Curators of the University of Missouri (University of Missouri)
• Original Assignee: Curators of the University of Missouri (University of Missouri)
• Inventors: Shyu, Chi-Ren, Scott, Grant Jason, Klaric, Matthew Nicholas, Davis, Curtis Herbert
• Granted Patent: US 8,001,115 B2
• Time in Patent Office: Days
• US Class Current: 707/728
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 30/422 Technical drawings; Geographical maps

Abstract

A method, system, and medium are provided for identifying terrestrial objects that have changed in a certain manner. One embodiment of the method includes receiving a query that includes one or more inputs, which are related to 1) a first terrestrial object (“first object”) and 2) source change-detection information that describes change associated with the first object; applying the query to a dataset that includes indexed information that describes the imagery; based on the one or more inputs, receiving a query result by identifying a set of regions in the dataset that are respectively associated with change information that is similar to that of the source change-detection information; and presenting on a presentation device indications of at least a portion of the identified set of regions.

Claims

1. One or more computer-readable media having computer-useable instructions embodied thereon for performing a method of utilizing high-resolution remotely sensed imagery (“

imagery”

) to identify terrestrial objects that have changed in a certain manner, the method comprising;

receiving a query that includes one or more inputs that indicate attributes of the terrestrial objects, wherein results of the query will be identified images, which

(1) were derived from the imagery, and

(2) are associated with the terrestrial objects, which have changed in ways similar to the certain manner;

from the one or more inputs of the query, determining a source set of change-detection information;

referencing a dataset that stores a plurality of sets of change-detection information that are respectively associated with a plurality of objects;

based on the source change-detection information, determining the results from the dataset, wherein the results include a set of images that includes content that is associated with change-detection information that is similar to the source change-detection information;

ranking at least a portion of images in the set of images based on their similarity to the source change-detection information, thereby providing a plurality or ranked images, each associated with a ranking value; and

presenting an indication of at least a portion of the results based on the ranking.

2. One or more computer-readable media having computer-useable instructions embodied thereon for performing a method of utilizing high-resolution remotely sensed imagery (“

imagery”

) to identify terrestrial objects that have changed in a certain manner, the method comprising;

receiving a query that includes one or more inputs that indicate attributes of the terrestrial objects, wherein results of the query will be identified images, which

(1) were derived from the imagery, and

(2) are associated with the terrestrial objects, which have changed in ways similar to the certain manner;

from the one or more inputs of the query, determining a source set of change-detection information that is associated with a source object;

referencing a dataset that stores a plurality of sets of change-detection information that are respectively associated with a plurality of objects;

based on the source change-detection information and on the source object, determining the results from the dataset, wherein the results include a set of images that include content that (1) has features similar to those of the source object and (2) that is associated with change-detection information that is similar to the source change-detection information;

ranking at least a portion of images in the set of images based on their similarity to the source object and to the source change-detection information, thereby providing a plurality of ranked images, each associated with a ranking value; and

presenting an indication of at least a portion of the results based on the ranking.

3. The media of claim 2, wherein the source and terrestrial objects include one or more of:

a geographic area; and

an item in a geographic area.

4. The media of claim 3, wherein the one or more inputs includes one or more of the following:

(1) a first image that depicts the source object in a first state and a second image that depicts the source object in a second state;

(2) a first image that depicts the source object in a first state and the source change-detection information that is associated with the source object and that describes change in the source object from the first state over time, such that the results returned are of objects that (a) appeared in an initial state similar to the first state of the source object and (b) that changed in a manner similar to that described by the source change-detection information;

(3) a second image that depicts the source object in a second state and the source change-detection information associated with the source object that indicates change in the source object to the second state over time, such that the results returned are of objects that (a) appeared in a subsequent state similar to the second state of the source object and (b) that changed in a way similar to that described by the source change-detection information; and

(4) the source change-detection information.

5. The media of claim 4, wherein the source change-detection information is derived by one or more of the following ways:

dynamically determining the change-detection information from the first and second images;

retrieving stored change-detection information that is previously and respectively stored in connection with the source object; and

receiving the source change-detection information as an upload from a communicating device.

6. The media of claim 5, wherein the content includes at least a portion of an image.

7. The media of claim 6, wherein determining the results includes identifying target objects that are similar to the source object, and wherein the identifying the target objects includes:

identifying a source feature set that describes a set of features associated with the source object;

comparing the source feature set against a plurality of stored feature sets of the dataset, wherein each stored feature set in the plurality is associated with a corresponding image; and

determining which of the plurality of stored feature sets most closely matches the source feature set.

8. The media of claim 7, wherein the source feature set includes a description of one or more of the following features associated with the source object:

linear features;

spatial features;

textural features;

spectral features;

shape features; and

scale changes.

9. The media of claim 7, wherein identifying the source features is accomplished by one or more of the following methods;

by referencing the source features in the dataset, the source features having previously been stored therein; and

by determining the source features on demand, wherein the source features have not been previously stored as part of the dataset.

10. The media of claim 2,

wherein determining the results further includes identifying target change-detection information that reflects change similar to that of the source set of change-detection information,

wherein the identifying target change-detection information includes comparing change features of the source change-detection information to features of the plurality of sets of change-detection information;

and

selecting objects associated with specific target change-detection information that has relatively fewer differences in change features based on the source set of change-detection information.

11. The media of claim 10, wherein the change features of the source change-detection information include one or more of:

textural features;

spectral features;

spatial features; and

linear features.

12. The media of claim 11, wherein the change features are describable by one or more respective variable query inputs that enable a weighting of one or more of the change features.

13. The media of claim 11, wherein the identifying target change-detection information includes identifying change associated with objects in the dataset that is of a similar change intensity to that of the source change-detection information.

14. The media of claim 2, wherein presenting the indication of at least a portion of the results includes presenting one or more of:

at least a portion of the images; and

indicia that identifies the at least a portion of the images.

15. One or more computer-readable media having computer-useable instructions embodied thereon for performing a method of utilizing high-resolution remotely sensed imagery (“

imagery”

) to identify terrestrial objects that have changed in a certain manner, the method comprising;

receiving a query that includes one or more inputs, which are related to

     1) a first terrestrial object (“

first object”

) and

     2) source change-detection information that describes change associated with the first object;

applying the query to a dataset that includes indexed information that describes the imagery;

based on the one or more inputs, receiving a query result by identifying a set of regions in the dataset that are respectively associated with change information that is similar to that of the source change-detection information; and

presenting on a presentation device indications of at least a portion of the identified set of regions.

16. The media of claim 15, wherein the one or more inputs include one or more of the following:

(1) a first image that depicts the first object in a first state and a second image that depicts the first object in a second state;

(2) a first image that depicts the first object in a first state and corresponding change-detection information that is associated with the first object and that describes change in the first object from the first state over time, such that the results returned are of objects that (a) appeared in an initial state similar to the first state of the first object and (b) that changed in a manner similar to that described by the source change-detection information, which in this case would be the corresponding change-detection information;

(3) a second image of the first object in a second state and the source change-detection information that is associated with the first object and that indicates change in the first object to the second state over time, such that the results returned are of objects that (a) appeared in a subsequent state similar to the second state of the first object and (b) that changed in a way similar to that described by the source change-detection information, which in this case would be the corresponding change-detection information; and

(4) the source change-detection information.

17. The media of claim 16, wherein the source change-detection information is characterized by one or more change features, and the one or more change features can each be weighted to vary a relevance that each feature has on returning the results.

18. The media of claim 17, further comprising ranking each region in the set of regions of the query result.

19. The media of claim 18, wherein the ranking of each region includes associating one or more ranking values with each region in the set of regions, and wherein the one or more ranking values indicates a relative similarity to:

the first image, which depicts the first object in the first state;

the second image, which depicts the first object in the second state;

the source change-detection information; and

a change map associated with the first object.

20. One or more computer-readable media having computer-useable instructions for performing a method of locating remotely sensed imagery of interest, the method comprising:

referencing first and second images that respectively depict a first geographic area in first and second states, wherein each of the first and second images contain remotely sensed imagery information;

automatically determining from the first and second images source change information that describes differences between the first and second images;

identifying a group of target geographic areas that form part of a stored dataset of imagery, which dataset includes a plurality of geographic areas, each geographic area in the plurality being associated with

(1) a pair of images, a before image and an after image, that respectively depict the each geographic area in a first state and in a second state, and

(2) corresponding change information (“

image-pair change information”

) that describes differences between the before and after images;

wherein each target geographic area in the group is associated with change information that is similar to the source change information; and

presenting results of a search, wherein the results include a selection of target geographic areas from the group of target geographic areas.

21. The media of claim 20, wherein each target geographic area is associated with:

a target before image that indicates a given target geographic area in a first state;

a target after image that indicates the given target geographic area in the second state; and

specific target change information that indicates differences between the target before and after images.

22. The media of claim 21, further comprising associating two ranking values with each result returned, wherein

a first ranking value indicates a similarity of one or more of,

(1) the target before image to the first image, and

(2) the target after image to the second image;

and

a second ranking value that indicates a similarity of the specific target change information to the source change information.