Computer System and Method for Classifying Temporal Patterns of Change in Images of an Area

• US 20180357517A1
• Filed: 06/09/2017
• Published: 12/13/2018
• Est. Priority Date: 06/09/2017
• Status: Active Grant

• Current Assignee: Uptake Technologies, Inc.
• Original Assignee: Uptake Technologies, Inc.
• Inventors: Gandenberger, Greg
• Granted Patent: US 10,255,526 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/241 relating to the classification model, e.g. parametric or non-parametric approaches
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal

Abstract

A set of successive images for a given area may comprise a first, second, and third images representing different times. Comparisons may be performed between the first image and the second image, the first image and the third image, and the second image and the third image. The respective outputs of the three pairwise comparisons may be evaluated to identify any sub-areas of the given area where one or more temporal patterns of change have occurred. For instance, any sub-area of the given area that exhibits a change between the first and second images, a change between the second and third images, and an absence of change between the second and third images may be identified as a persistent change. An indication that the temporal pattern of change has occurred at each identified sub-area of the given area may then be output to a client station.

Claims

1. A method comprising:

receiving a set of successive images for a given area from an image data source via a communication network, wherein the set of successive images comprises a first image captured at a first time, a second image captured at a second time, and third image captured at a third time, and wherein the given area comprises a plurality of sectors;

determining, for each respective sector of the given area, (i) a first likelihood of change between the first image captured at the first time and the second image captured at the second time, (ii) a second likelihood of change between the first image captured at the first time and the third image captured at the third time, and (iii) a third likelihood of change between second image captured at the second time and the third image captured at the third time;

evaluating the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a given type of change; and

outputting, to a client station via the communication network, data indicating that the given type of change has occurred at each identified sector of the given area.

2. The method of claim 1, wherein the given type of change comprises a persistent change, and wherein evaluating the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a persistent change comprises identifying any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that exceeds a second threshold, and (iii) a third likelihood of change that falls below a third threshold.

3. The method of claim 1, wherein the given type of change comprises an ongoing change, and wherein evaluating the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits an ongoing change comprises identifying any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that exceeds a second threshold, and (iii) a third likelihood of change that exceeds a third threshold.

4. The method of claim 1, wherein the given type of change comprises a reverting change, and wherein evaluating the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a reverting change comprises identifying any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that falls below a second threshold, and (iii) a third likelihood of change that exceeds a third threshold.

5. The method of claim 1, wherein the first image, second image, and third image each comprise a respective set of image data organized into pixel blocks that each correspond to a respective sector of the given area, and wherein determining, for each respective sector of the given area, (i) a first likelihood of change between the first image captured at the first time and the second image captured at the second time, (ii) a second likelihood of change between the first image captured at the first time and the third image captured at the third time, and (iii) a third likelihood of change between second image captured at the second time and the third image captured at the third time comprises:

for each respective sector of the given area, (i) comparing the pixel block corresponding to the sector from the first image to the complementary pixel block corresponding to the sector from the second image and thereby determining the first likelihood of change for the sector, (ii) comparing the pixel block corresponding to the sector from the first image to the complementary pixel block corresponding to the sector from the third image and thereby determining the second likelihood of change for the sector, and (iii) comparing the pixel block corresponding to the sector from the second image to the complementary pixel block corresponding to the sector from the third image and thereby determining a first likelihood of change for the sector.

6. The method of claim 1, wherein the data indicating that the given type of change has occurred at each identified sector of the given area comprises location data for each identified sector.

7. The method of claim 1, wherein the data indicating that the given type of change has occurred at each identified sector of the given area is included as part of an array of indicators that each correspond to a respective sector of the given area, and wherein each indicator in the array of indicators provides an indication of whether the respective sector exhibits the given type of change.

8. The method of claim 1, further comprising:

instructing the client station to display a map of the given area that includes a visual representation of the data indicating that the given type of change has occurred at each identified sector of the given area.

15. The method of claim 1, further comprising:

instructing the client station to display a map of the given area that includes a visual representation of the data indicating that a persistent change has occurred at the at least one sub-area of the given area.

9. A method comprising:

receiving a set of successive images for a given area from an image data source via a communication network, wherein the set of successive images comprises a first image captured at a first time, a second image captured at a second time, and third image captured at a third time;

performing a first comparison between the first image captured at the first time and the second image captured at the second time to detect any change between the first and second images;

performing a second comparison between the first image captured at the first time and the third image captured at the third time to detect any change between the first and third images;

performing a third comparison between the second image captured at the second time and the third image captured at the third time to detect an absence of any change between the second and third images;

based on the first, second, and third comparisons, identifying at least one sub-area of the given area that exhibits a change between the first and second images, a change between the second and third images, and an absence of change between the second and third images; and

outputting, to a client station via the communication network, data indicating that a persistent change has occurred at the at least one sub-area of the given area.

10. The method of claim 9, further comprising:

before receiving the set of successive images for the given area from an image data source, (a) receiving, from the client station, a request to identify any persistent change in the given area and (b) in response to receiving the request from the client station, transmitting, to the image data source, a request for the set of successive images for the given area.

11. The method of claim 9, wherein:

performing the first comparison between the first image captured at the first time and the second image captured at the second time to detect any change between the first and second images comprises, for each of a plurality of sub-areas of the given area, (a) determining a respective first likelihood of change between the first image captured at the first time and the second image captured at the second time and (b) determining whether the respective first likelihood of change exceeds a first threshold;

performing the second comparison between the first image captured at the first time and the third image captured at the third time to detect any change between the first and third images comprises, for each of the plurality of sub-areas of the given area, (a) determining a respective second likelihood of change between the first image captured at the first time and the third image captured at the third time and (b) determining whether the respective second likelihood of change exceeds a second threshold; and

performing the third comparison between the second image captured at the second time and the third image captured at the third time to detect an absence of any change between the second and third images comprises, for each of the plurality of sub-areas of the given area, (a) determining a respective third likelihood of change between the second image captured at the second time and the third image captured at the third time and (b) determining whether the respective third likelihood of change falls below a third threshold.

12. The method of claim 11, wherein identifying at least one sub-area of the given area that exhibits a change between the first and second images, a change between the second and third images, and an absence of change between the second and third images comprises identifying at least one sub-area having a respective first likelihood of change that exceeds the first threshold, a respective second likelihood of change that exceeds the second threshold, and a respective third likelihood of change that falls below the third threshold.

13. The method of claim 9, wherein the data indicating that a persistent change has occurred at the at least one sub-area of the given area comprises location data for the at least one sub-area.

14. The method of claim 9, wherein the data indicating that a persistent change has occurred at the at least one sub-area of the given area is included as part of an array of indicators that each correspond to a respective sub-area of the given area, and wherein each indicator in the array of indicators provides an indication of whether the respective sub-area exhibits a persistent change.

16. A computing system comprising:

a network interface configured to communicatively couple the computing system to (a) at least one image data source and (b) at least one client station;

at least one processor;

a non-transitory computer-readable medium; and

program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor to cause the computing system to;

receive a set of successive images for a given area from an image data source via the network interface, wherein the set of successive images comprises a first image captured at a first time, a second image captured at a second time, and third image captured at a third time, and wherein the given area comprises a plurality of sectors;

determine, for each respective sector of the given area, (i) a first likelihood of change between the first image captured at the first time and the second image captured at the second time, (ii) a second likelihood of change between the first image captured at the first time and the third image captured at the third time, and (iii) a third likelihood of change between second image captured at the second time and the third image captured at the third time;

evaluate the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a given type of change; and

output, to a client station via the network interface, data indicating that the given type of change has occurred at each identified sector of the given area.

17. The computer system of claim 16, wherein the given type of change comprises a persistent change, and wherein the program instructions that are executable by the at least one processor to cause the computing system to evaluate the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a persistent change comprise program instructions that are executable by the at least one processor to cause the computing system to identify any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that exceeds a second threshold, and (iii) a third likelihood of change that falls below a third threshold.

18. The computer system of claim 16, wherein the given type of change comprises an ongoing change, and wherein the program instructions that are executable by the at least one processor to cause the computing system to evaluate the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits an ongoing change comprise program instructions that are executable by the at least one processor to cause the computing system to identify any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that exceeds a second threshold, and (iii) a third likelihood of change that exceeds a third threshold.

19. The computer system of claim 16, wherein the given type of change comprises a reverting change, and wherein the program instructions that are executable by the at least one processor to cause the computing system to evaluate the first, second, and third likelihood of change for each respective sector of the given area to identify any sector of the given area that exhibits a reverting change comprise program instructions that are executable by the at least one processor to cause the computing system to identify any sector of the given area having (i) a first likelihood of change that exceeds a first threshold, (ii) a second likelihood of change that falls below a second threshold, and (iii) a third likelihood of change that exceeds a third threshold.

20. A computing system comprising:

a network interface configured to communicatively couple the computing system to (a) at least one image data source and (b) at least one client station;

at least one processor;

a non-transitory computer-readable medium; and

program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor to cause the computing system to;

receive a set of successive images for a given area from an image data source via the network interface, wherein the set of successive images comprises a first image captured at a first time, a second image captured at a second time, and third image captured at a third time;

perform a first comparison between the first image captured at the first time and the second image captured at the second time to detect any change between the first and second images;

perform a second comparison between the first image captured at the first time and the third image captured at the third time to detect any change between the first and third images;

perform a third comparison between the second image captured at the second time and the third image captured at the third time to detect an absence of any change between the second and third images;

based on the first, second, and third comparisons, identify at least one sub-area of the given area that exhibits a change between the first and second images, a change between the second and third images, and an absence of change between the second and third images; and

output, to a client station via the network interface, data indicating that a persistent change has occurred at the at least one sub-area of the given area.