Automatic generation of metadata for a digital image based on ambient conditions

• US 8,842,197 B2
• Filed: 11/30/2005
• Issued: 09/23/2014
• Est. Priority Date: 11/30/2005
• Status: Active Grant

• Current Assignee: Scenera Mobile Technologies LLC (Scenera Research LLC)
• Original Assignee: Scenera Mobile Technologies LLC (Scenera Research LLC)
• Inventors: Singh, Munindar P.
• Primary Examiner(s): OSINSKI, MICHAEL S
• Application Number:
  US11/164,641
• Publication Number:
  US 20070127833A1
• Time in Patent Office: 3,219 Days
• Field of Search: 348/211.2, 348/143, 348/239, 348/231.5, 348/231.3, 382/254, 382/305
• US Class Current: 348/231.3
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: H04N 2201/3253 Position information, e.g. geographical position at time of capture, GPS data

Abstract

A method and system is provided for automatically generating metadata for a digital image based on ambient conditions. Aspects of the preferred embodiment include determining a plurality of ambient conditions associated with a location of a subject of a digital image captured with a mobile image capture device, the ambient conditions existing at a time related to a time of capture of the digital image; aggregating the plurality of ambient conditions into at least one ambient environment descriptor based on user-definable aggregation rules; and associating the ambient environment descriptor with the digital image as metadata.

Claims

1. A method for automatically generating metadata for a user for a digital image, comprising:

obtaining user-definable aggregation rules of the user that includes at least one of;

a rule indicating that “

muggy”

is specified when a plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioninq to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioninq to “

brightening”

, “

warming”

, and with “

falling humidity”

;

determining a plurality of ambient conditions existing at a time related to a time of capture of the digital image and associated with a location of a subject of the digital image captured with a mobile image capture device even when the mobile image capture device is in a different location, wherein determining the plurality of ambient conditions includes determining variations of the ambient conditions over time by receiving readings of the ambient conditions at a plurality of times including at least one of a time before the time of capture, at the time of capture, and after the time of capture;

aggregating and transforming data associated with the plurality of ambient conditions into at least one ambient trend descriptor based on the obtained user- definable aggregation rules wherein the aggregating includes aggregating the variations of the ambient conditions determined over the plurality of times;

associating the ambient trend descriptor with the digital image as metadata; and

enabling a user to search for the digital image based on the at least one ambient trend descriptor.

2. The method of claim 1 wherein determining the plurality of ambient conditions at the location of the subject of the digital image further comprises receiving the ambient conditions from at least one of;

an online information source, and

from sensors of the image capture device.

7. The method of claim 1 further including providing a user interface through which the aggregation rules are configured to define the at least one ambient environment descriptor.

8. The method of claim 7 wherein the aggregation rules are configured for each individual end-user, thereby allowing subjective ambient environment descriptors to be defined.

9. The method of claim 7 wherein the aggregation rules are configured for different demographic groups.

15. The method of claim 1 wherein enabling a user to search for the digital image based on the ambient environment descriptor includes allowing searches to be performed for the digital image by specifying desired metadata including the at least one ambient environment descriptor.

16. The method of claim 15 further comprising allowing searches to be performed for the digital image by specifying variations of the ambient conditions over time for both a fixed location of the subject of the digital image, and a location of the image capture device.

3. A method for automatically generating metadata for a user for a digital image, comprising:

obtaining user-definable aggregations rules of the user that includes at least one of;

a rule indicating that “

muggy”

is specified when a plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioning to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioning to “

brightening”

, “

warming”

, and with “

falling humidity”

;

determining a plurality of ambient conditions existing at a time related to a time of capture of the digital image and associated with a location of a subject of the digital image captured with a mobile image capture device even when the mobile image capture device is in a different location, wherein determining the plurality of ambient conditions includes determining variations of the ambient conditions over time by receiving readings of the ambient conditions for at least one of a fixed location of the subject of the digital image and a location of the image capture device at a plurality of times including at least one of a time before the time of capture, at the time of capture, and after the time of capture;

aggregating and transforming data associated with the plurality of ambient conditions into at least one ambient environment descriptor based on the obtained user- definable aggregation rules wherein the aggregating includes aggregating the variations of the ambient conditions determined over the plurality of times;

associating the ambient environment descriptor with the digital image as metadata; and

enabling a user to search for the digital image based on the at least one ambient environment descriptor.

4. The method of claim 3 wherein the ambient conditions include weather-related ambient conditions and non-weather related ambient conditions.

5. The method of claim 4 wherein the weather-related ambient conditions include any combination of temperature, humidity, barometric pressure, visibility, season, and wind.

6. The method of claim 4 wherein the non-weather related ambient conditions include any combination of at least one of location, heading, elevation, and brightness level of at least one of the subject and the image capture device.

10. The method of claim 3 wherein aggregating the plurality of ambient conditions into an ambient environment descriptor further comprises,

receiving values for each of the ambient conditions within a specified time period before and after the time of capture;

and

for each of the ambient conditions,

summarizing the values of the ambient condition by applying an value descriptor to the ambient condition; and

summarizing changes in the values of the ambient condition by applying a trend descriptor to the ambient condition.

11. A method for automatically generating metadata for a digital image, comprising:

determining a plurality of ambient conditions associated with a location of a subject of the digital image captured with a mobile image capture device even when the mobile image capture device is in a different location, the ambient conditions existing at a time related to a time of capture of the digital image;

aggregating the plurality of ambient conditions and transforming data associated with the plurality of ambient conditions into at least one ambient environment descriptor based on user-definable aggregation rules wherein aggregating the plurality of ambient conditions into an ambient environment descriptor further comprises receiving values for each of the ambient conditions within a specified time period before and after the time of capture,

for each of the ambient conditions, summarizing the values of the ambient condition by applying an value descriptor to the ambient condition, and summarizing changes in the values of the ambient condition by applying a trend descriptor to the ambient condition, aggregating related ones of the ambient conditions by,

summarizing the value descriptors applied to the related ambient conditions using the user-definable rules as a lookup table to apply a combination value descriptor and

summarizing the trend descriptors applied to the related ambient conditions using the user-definable rules as a lookup table to apply a combination trend descriptor; and

associating the ambient environment descriptor with the digital image as metadata.

12. The method of claim 11 wherein aggregating the plurality of ambient conditions into an ambient environment descriptor further comprises storing the combination value descriptors and the combination trend descriptors as the image metadata.

13. The method of claim 12 wherein aggregating the plurality of ambient conditions into an ambient environment descriptor further comprises storing the value descriptors and the trend descriptors for each of the ambient conditions as the image metadata.

14. The method of claim 12 wherein determining the plurality of ambient conditions further comprises determining variations of the ambient conditions over time for both a fixed location of the subject of the digital image, and a location of the image capture device.

17. A system for automatically generating metadata for a user for a digital image, comprising:

a mobile image capture device for capturing the digital image;

means for determining a plurality of ambient conditions existing at a time related to a time of capture of the digital image and associated with a location of a subject of the digital image device even when the digital image device is in a different location;

a metadata application component for;

automatically generating the metadata for the digital images by obtaining user-definable aggregation rules of the user that includes at least one of;

a rule indicating that “

muggy”

is specified when the plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioning to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioning to “

brightening”

, “

warming”

, and with “

falling humidity,”

aggregating the plurality of ambient conditions into at least one ambient environment descriptor based on the obtained user-definable aggregation rules, for associating the ambient environment descriptor with the digital image as metadata, wherein the aggregating includes aggregating variations of the ambient conditions determined over a plurality of times, and enabling a user to search for the digital image based on the at least one ambient environment descriptor.

18. The system of claim 17 wherein the means for determining a plurality of ambient conditions determines variations of the ambient conditions over time by receiving readings of the ambient conditions at a plurality of times including at least one of a time before the time of capture, at the time of capture, and after the time of capture.

19. The system of claim 18 wherein the means for determining a plurality of ambient conditions determines weather-related ambient conditions and non- weather related ambient conditions, wherein the weather-related ambient conditions include any combination of temperature, humidity, barometric pressure, visibility, season, and wind, and the non-weather related ambient conditions include any combination of location, heading, elevation, and brightness level of at least one of the subject and the image capture device.

20. The system of claim 19 wherein the means for determining a plurality of ambient conditions further comprises ambient condition determining means for determining at least one of,

variations of ambient conditions over time at the fixed location of the subject of the digital image, referred to as picture location (PICLOC) data, and

variations of ambient conditions over time at the location of the image capture device, referred to camera location (CAMLOC) data.

21. The system of claim 20 wherein the ambient condition determining means include at least one of,

an ambient conditions site on a network that provides the PICLOC data based on a specified time and location, and

sensors in the image capture device for sensing ambient condition values in real- time and for storing the ambient condition as the CAMLOC data.

22. The system of claim 17 wherein the metadata application component includes a user interface for allowing the user to configure the aggregation rules to define the at least one ambient environment descriptor, and to perform searches for the digital image by specifying desired metadata including the at least one ambient environment descriptor.

23. The system of claim 17 wherein the metadata application component aggregates the plurality of ambient conditions into an ambient environment descriptor by,

receiving values for each of the ambient conditions within a specified time period before and after the time of capture;

and

for each of the ambient conditions,

summarizing the values of the ambient condition by applying an value descriptor to the ambient condition; and

summarizing changes in the values of the ambient condition by applying a trend descriptor to the ambient condition.

24. A system for automatically generating metadata for a user for a digital image, comprising:

a mobile image capture device for capturing the digital image;

means for determining a plurality of ambient conditions existing at a time related to a time of capture of the digital image and associated with a location of a subject of the digital image device even when the digital image device is in a different location, wherein the means for determining a plurality of ambient conditions determines variations of the ambient conditions over time by receiving readings of the ambient conditions at a plurality of times including at least one of a time before the time of capture, at the time of capture, and after the time of capture; and

a metadata application component for obtaining user-definable aggregation rules for the user, automatically generating the metadata for the digital images by aggregating the plurality of ambient conditions into at least one ambient environment descriptor based on the obtained user-definable aggregation rules, and for associating the ambient environment descriptor with the digital image as metadata, wherein the metadata application component aggregates the plurality of ambient conditions over the plurality of times into an ambient environment descriptor by;

receiving values for each of the ambient conditions within a specified time period before and after the time of capture; and

for each of the ambient conditions;

summarizing the values of the ambient condition by applying an value descriptor to the ambient condition; and

summarizing changes in the values of the ambient condition by applying a trend descriptor to the ambient condition

aggregating related ones of the ambient conditions by,

summarizing the value descriptors applied to the related ambient conditions using the user-definable able rules as lookup table to apply a combination value descriptor; and

summarizing the trend descriptors applied to the related ambient conditions using the user-definable rules as lookup table to apply a combination trend descriptor; and

enabling a user to search for the digital image based on the at least one ambient environment descriptor.

25. The system of claim 24 wherein the metadata application component aggregates the plurality of ambient conditions into an ambient environment descriptor by storing at least one of the combination value descriptors and the combination trend descriptors as the image metadata and storing the value descriptors and the trend descriptors for each of the ambient conditions as the image metadata.

26. An executable software product stored on a non- transitory computer-readable medium containing program instructions for automatically generating metadata for a digital image, the program instructions including:

obtaining user-definable aggregation rules that includes at least one of;

a rule indicating that “

muggy”

is specified when a plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioning to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioning to “

brightening”

, “

warming”

, and with “

falling humidity”

;

determining a plurality of ambient conditions existing at a time related to a time of capture of the digital image and associated with a location of a subject of the digital image captured with a mobile image capture device even when the mobile image capture device is in a different location;

aggregating the plurality of ambient conditions into at least one ambient environment descriptor based on the obtained user-definable aggregation rules, wherein the aggregating includes aggregating variations of the ambient conditions determined over a plurality of times;

associating the ambient environment descriptor with the digital image as metadata; and

enabling the user to search for the digital image based on the ambient environment descriptor.

27. A method for automatically generating and searching metadata for a digital image, comprising:

determining a plurality of ambient conditions over time at a location of a subject of the digital image captured with a mobile image capture device even when the image capture device is in a different location, the ambient conditions existing at a time related to a time of capture of the digital image;

aggregating the plurality of ambient conditions into at least one ambient trend descriptor based on user-definable aggregation rules, wherein the aggregating includes aggregating variations of the ambient conditions determined over a plurality of times and the user-definable aggregation rules includes at least one of;

a rule indicating that “

muggy”

is specified when the plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioninq to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioning to “

brightening”

, “

warming”

, and with “

falling humidity”

;

associating the ambient trend descriptor with the digital image as metadata; and

enabling a user to search for the digital image based on the ambient trend descriptor.

28. A method for searching images based on automatic generation of metadata for a digital image, comprising:

receiving a search query from a user that includes at least one ambient environment descriptor associated with at least one digital image;

obtaining the user'"'"'s user-definable aggregation rules that includes at least one of;

a rule indicating that “

muggy”

is specified when a plurality of ambient conditions is “

warm” and

“

very humid”

;

a rule indicating that “

sweltering”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

;

a rule indicating that “

balmy”

is specified when the plurality of ambient conditions is “

mild”

, “

breezy”

, and “

partially humid”

;

a rule indicating that “

driving rain”

is specified when the plurality of ambient conditions is “

rainy” and

“

windy”

;

a rule indicating that “

monsoon-like”

is specified when the plurality of ambient conditions is “

warm” and

“

gusty” and

“

rainy” and

“

winds from the South to South-West”

;

a rule indicating that “

Sudden shower”

is specified when the plurality of ambient conditions is “

hot” and

“

humid”

transitioning to “

cooler” and

“

rainy”

; and

a rule indicating that “

Clearing”

is specified when the plurality of ambient conditions is “

foggy”

, “

cold”

, and “

partly humid”

transitioning to “

brightening”

, “

warming”

, and with “

falling humidity”

;

evaluating the search query based on the user-definable aggregation rules to retrieve the at least one digital image associated with the at least one ambient environment descriptor; and

displaying the retrieved at least one image.

29. The method of claim 28, wherein obtaining the user'"'"'s user-definable aggregation rules comprises:

obtaining aggregation rules based on the user'"'"'s demographics; and

wherein evaluating the search query based on the user-definable aggregation rules to retrieve images associated with the at least one ambient environment descriptor comprises evaluating the search query based on the aggregation rules based on the user'"'"'s demographics to retrieve images associated with the at least one ambient environment descriptor.

30. The method of claim 29 wherein the demographics are defined culturally and geographically

31. The method of claim 29 wherein the aggregations rules are defined specific to an affinity group.

32. The method of claim 28 wherein the user-definable rules include rules defining ambient condition terms including a plurality of terms selected from “

warm”

, “

hot”

, “

humid”

, “

very humid”

, “

partially humid”

, “

mild”

, “

breezy”

, “

rainy”

, “

windy”

, “

gusty”

, “

cool”

, “

cold”

, “

warming”

, “

falling”

, “

rising”

, “

steady”

, “

decreasing”

, and “

increasing”

.