Identifying and generating color and texture video cohorts based on video input

• US 8,749,570 B2
• Filed: 12/11/2008
• Issued: 06/10/2014
• Est. Priority Date: 12/11/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Angell, Robert Lee, Friedlander, Robert R, Kraemer, James R, Borger, Sergio, Patnaik, Yashodhara M.
• Primary Examiner(s): Thompson, James A
• Assistant Examiner(s): Merouan, Abderrahim
• Application Number:
  US12/333,273
• Publication Number:
  US 20100150457A1
• Time in Patent Office: 2,007 Days
• Field of Search: 345/419, 345/418, 345/582, 382/103, 382/104, 382/107, 382/115, 382/173, 382/197, 382/224, 382/228, 348/134, 348/135, 348/143, 348/148, 348/149, 348/150, 348/166, 348/169, 348/170, 348/172
• US Class Current: 345/582
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model

Abstract

A computer implemented method, apparatus, and computer program product for generating video based cohorts. Digital video data is processed to identify a set of color and texture based attributes associated with the set of objects. The digital video data comprises metadata describing the set of objects. The set of color and texture based attributes are analyzed using cohort criteria to form a result. The cohort criteria specify attributes that are associated with members of a given cohort. A set of cohorts is generated based on the result. Each cohort in the set of cohorts comprises a subset of objects from the set of objects that share at least one color and texture based attribute in common.

Claims

1. A computer implemented method for generating and utilizing video based cohorts, the computer implemented method comprising:

processing digital video data, by a video analysis engine, to identify a set of color attributes and texture based attributes associated with clothing worn by a set of objects, wherein the set of objects are persons wearing an item of clothing manufactured by a specific manufacturer, wherein the digital video data comprises metadata describing the set of objects, wherein the texture based attributes describe whether the item of clothing is smooth or rough, wherein the item of clothing is a particular color, and wherein the digital video data comprises video images of the set of objects that are captured by a plurality of cameras;

adjusting colors of the video images by identifying light sources that illuminate the set of objects and shadows that fall on the set of objects, wherein the light sources and the shadows have been predetermined to alter true colors of a corporate logo that is affixed to the item of clothing, wherein said adjusting colors returns an image of the corporate logo to its true colors, and wherein the corporate logo identifies the specific manufacturer of the item of clothing being worn by the persons whose images are captured by the plurality of cameras;

analyzing the set of color and texture based attributes using cohort criteria to identify the item of clothing and the corporate logo captured by the plurality of cameras;

generating and storing a set of video based cohorts, wherein each cohort in the set of video based cohorts comprises a subset of objects, from the set of objects, that share at least one color and texture based attribute; and

predicting, by an inference engine, whether the item of clothing being worn by the persons viewed by the plurality of cameras and by persons from a cohort from the set of video based cohorts, will increase in popularity in a particular geographic region based on how many persons of a predetermined age group are viewed, by the plurality of cameras, while wearing a copy of the item of clothing.

2. The computer implemented method of claim 1, wherein the set of color and texture based attributes comprises an identification of a color of a portion of clothing worn by an object in the set of objects.

3. The computer implemented method of claim 1, wherein the set of color and texture based attributes comprises properties of a color associated with a portion of clothing worn by an object in the set of objects.

4. The computer implemented method of claim 1, wherein the set of color and texture based attributes comprises an identification of a pattern of colors associated with clothing worn by an object in the set of objects.

5. The computer implemented method of claim 1, wherein the set of color and texture based attributes comprises an identification of a texture associated with a portion of a surface of clothing worn by an object in the set of objects.

6. The computer implemented method of claim 1, further comprising:

receiving the set of video based cohorts by an inference engine; and

processing the set of video based cohorts by the inference engine, wherein the inference engine uses the set of video based cohorts to generate a set of inferences, and wherein the set of inferences identifies a predicted future activity by members described by the set of video based cohorts.

7. A computer program product for generating video cohort data, the computer program product comprising:

a computer readable storage device having computer usable program code embodied therewith, the computer usable program code comprising;

computer usable program code to process digital video data, by a video analysis engine, to identify a set of color attributes and texture based attributes associated with clothing worn by a set of objects, wherein the set of objects is persons wearing an item of clothing manufactured by a specific manufacturer, wherein the digital video data comprises metadata describing the set of objects, wherein the texture based attributes describe whether the item of clothing is smooth or rough, and wherein the digital video data comprises video images, of the set of objects, that are captured by a plurality of cameras;

computer usable program code to adjust colors of the video images by identifying light sources that illuminate the set of objects and shadows that fall on the set of objects, wherein the light sources and the shadows have been predetermined to alter true colors of a corporate logo that is affixed to the item of clothing, wherein adjusting said colors returns an image of the corporate logo to its true colors, and wherein the corporate logo identifies the specific manufacturer of the item of clothing being worn by persons whose images are captured by the plurality of cameras;

computer usable program code to analyze the set of color attributes and texture based attributes using cohort criteria to identify the item of clothing and the corporate logo captured by the plurality of cameras;

computer usable program code to generate and store a set of video based cohorts based on the result, wherein each cohort in the set of video based cohorts comprises a subset of objects, from the set of objects, that share at least one color attribute and one texture based attribute; and

computer usable program code to predict whether the item of clothing being worn by the persons and members of a cohort from the set of video based cohorts, will increase in popularity in a particular geographic region based on how many persons are viewed, by the plurality of cameras, while wearing a copy of the item of clothing.

8. The computer program product of claim 7, wherein the set of color and texture based attributes comprises an identification of a color of a portion of clothing worn by an object in the set of objects.

9. The computer program product of claim 7, wherein the set of color and texture based attributes comprises properties of a color associated with a portion of clothing worn by an object in the set of objects.

10. The computer program product of claim 7, wherein the set of color and texture based attributes comprises an identification of a pattern of colors associated with a portion of clothing worn by an object in the set of objects.

11. The computer program product of claim 7, wherein the set of color and texture based attributes comprises an identification of a texture associated with a portion of a surface of clothing worn by an object in the set of objects.

12. The computer program product of claim 7, further comprising:

computer usable program code to receive the set of video based cohorts by an inference engine; and

computer usable program code to process the set of video based cohorts by the inference engine, wherein the inference engine uses the set of video based cohorts to generate a set of inferences.

13. An apparatus comprising:

a bus system;

a communications system coupled to the bus system;

a memory connected to the bus system, wherein the memory includes computer usable program code; and

a processing unit coupled to the bus system, wherein the processing unit executes the computer usable program code to process digital video data, by a video analysis engine, to identify a set of color attributes and texture based attributes associated with clothing worn by a set of objects, wherein the set of objects are persons wearing an item of clothing manufactured by a specific manufacturer, wherein the digital video data comprises metadata describing the set of objects, wherein the texture based attributes describe whether the item of clothing is smooth or rough, and wherein the digital video data comprises video images of the set of objects that are captured by a plurality of cameras;

adjust colors of the video images by identifying light sources that illuminate the set of objects and shadows that fall on the set of objects, wherein the light sources and the shadows have been predetermined to alter true colors of a corporate logo that is affixed to the item of clothing, wherein adjusting said colors returns an image of the corporate logo to its true colors, and wherein the corporate logo identifies the specific manufacturer of the item of clothing being worn by the persons whose images are captured by the plurality of cameras;

analyze the set of color attributes and texture based attributes using cohort criteria to identify the item of clothing and the corporate logo captured by the plurality of cameras;

generate and store a set of video based cohorts based on the result, wherein each cohort in the set of video based cohorts comprises a subset of objects, from the set of objects, that share at least one color attribute and texture based attribute; and

predict whether the item of clothing being worn by the persons and members of a cohort from the set of video based cohorts, will increase in popularity in a particular geographic region based on how many persons are viewed, by the plurality of cameras, while wearing a copy of the item of clothing.

14. The apparatus of 13, wherein the processing unit executes the computer usable program code to receive the set of video based cohorts by an inference engine and process the set of video based cohorts by the inference engine, wherein the inference engine uses the set of video based cohorts to generate a set of inferences.