DATA DIFFERENCE GUIDED IMAGE CAPTURING

• US 20120027250A1
• Filed: 07/28/2010
• Published: 02/02/2012
• Est. Priority Date: 07/28/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Omer, Ido, Ofek, Eyal
• Granted Patent: US 8,503,794 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

Methods and apparatuses are disclosed. Previously stored images of one or more geographic areas may be viewed by online users. A new low-resolution image may be acquired and aspects of the new low-resolution image may be compared with a corresponding one of the previously stored images to determine an amount of change. A determination may be made regarding whether to acquire a new high-resolution image based on the determined amount of change and a freshness score associated with the one of the previously stored images. In another embodiment, a new image may be captured and corresponding location data may be obtained. A corresponding previously stored image may be obtained and compared with the new image to determine an amount of change. The new image may be uploaded to a remote computing device based on the determined amount of change and a freshness score of the previously stored image.

Claims

1. A method for guiding data capturing comprising:

obtaining, by a computing device, a freshness score of a previously stored high-resolution aerial image of a geographic area;

obtaining, by the computing device, a recent low-resolution aerial image of the geographic area;

comparing, by the computing device, aspects of the recent low-resolution aerial image with aspects of the previously stored high-resolution aerial image to determine an amount of change; and

determining, by the computing device, whether to order new high-resolution aerial images based on the freshness score and the determined amount of change.

2. The method of claim 1, wherein the freshness score is at least partially based on an age of the previously stored high-resolution aerial image, such that a smaller minimum amount of change with respect to an older high-resolution aerial image causes the determining to determine that a new high-resolution aerial image is to be obtained than a minimum amount of change with respect to a newer previously stored high-resolution aerial image.

3. The method of claim 1, wherein the recent low-resolution aerial image and the previously-obtained high-resolution aerial image were captured during a same season in different years in order to reduce an effect of seasonal differences.

4. The method of claim 3, wherein the current low-resolution aerial image and the previously stored high-resolution aerial image were captured by a same satellite.

5. The method of claim 1, wherein the amount of change is determined based on a change in at least one item from a group of items consisting of a color distribution in an area, a spectral reflectance in the area, and textures in the area.

6. The method of claim 1, wherein the comparing further comprises

hallucinating a synthetic high-resolution image from the obtained recent low-resolution aerial image after the determining determines that a new high-resolution image is to be ordered.

7. The method of claim 1, wherein the amount of change is further determined based on non-image data.

8. A computing device comprising:

an interface for connecting to an image capturing device;

at least one processor;

a storage device;

a communication interface for communicating with at least one other computing device;

a bus connecting the at least one processor with the interface, the storage device, and the communication interface; and

a memory connected to the at least one processor via the bus, the memory including instructions for the at least one processor to perform a method comprising;

receiving captured image data from the image capturing device via the interface,

requesting and downloading, via the communication interface, online image data corresponding to the captured image data,

determining an amount of change between the received captured image data and the downloaded online image data,

determining whether to upload the received captured image data to a remote computing device based, at least partially, on the determined amount of change, and

uploading the received captured image data to the remote computing device only when the determining whether to upload the received captured image data determines that the received captured image data is to be uploaded.

9. The computing device of claim 8, wherein:

the downloaded online image data includes a freshness score that represents a probability that the online image data should be updated, and

the determining whether to upload the received captured image data is further based on the freshness score, such that an amount of change with respect to older online image data is smaller than an amount of change with respect to newer online image data to cause a determination to upload the received captured image data.

10. The computing device of claim 9, wherein the method further comprises displaying of the freshness score.

11. The computing device of claim 8, wherein the determining an amount of change further comprises:

using stereo video to estimate a size of an object, and

removing the object from consideration when calculating the amount of change when the object is estimated to be a size of a person.

12. The computing device of claim 8, wherein the determining an amount of change further comprises:

limiting the determining of the amount of change to static buildings included in a scene represented by the captured image data.

13. The computing device of claim 12, wherein the limiting the determining of the amount of change further comprises:

using at least one technique from a group of techniques comprising face detection, pedestrian detection, vehicle detection, motion detection, and foreground object detection to eliminate an effect of some objects on the determined amount of change.

14. The computing device of claim 8, wherein the determining an amount of change further comprises:

recovering text from the captured image data, and

comparing the recovered text from the captured image data with known data.

15. A method for guiding capturing of image data, the method comprising:

comparing, by the at least one computing device, recently captured image data for a geographic area with previously stored image data for the geographic area in order to determine an amount of change; and

determining, by the at least one computing device, whether the previously-stored image data is to be updated based on a freshness score of the previously stored image data and the determined amount of change.

16. The method of claim 15, wherein:

the recently captured image data is either low-resolution aerial image data or street level image data.

17. The method of claim 15, wherein:

the recently captured image data is low-resolution image data, and

the method further comprises

hallucinating a synthetic high resolution image based on the low-resolution image data and the previously stored image data when the determining determines that the previously stored image data is to be updated; and

presenting the synthetic high resolution image to a user in response to receiving a request from the user.

18. The method of claim 17, further comprising:

replacing the synthetic high resolution image with a recent high-resolution image.

19. The method of claim 15, further comprising:

obtaining non-image data related to the previously-stored image data; and

determining whether the previously stored image data is to be updated based, at least partially, on the non-image data and a freshness score associated with the previously stored image data.

20. The method of claim 15, further comprising:

obtaining a plurality of user-provided online image data;

comparing the plurality of user-provided online image data with corresponding ones of the previously stored image data; and

using only ones of the plurality of user-provided online image data having new information with respect to the corresponding ones of the previously stored image data to update the corresponding ones of the previously stored image data.