Generating cohorts based on attributes of objects identified using video input

• US 8,417,035 B2
• Filed: 12/12/2008
• Issued: 04/09/2013
• Est. Priority Date: 12/12/2008
• 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.
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US12/333,326
• Publication Number:
  US 20100150458A1
• Time in Patent Office: 1,579 Days
• Field of Search: 382/181, 382/209, 382/224, 382/225, 382/305
• US Class Current: 382/181
• CPC Class Codes: G06F 16/70 of video data

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 size and shape based attributes associated with the set of objects. The digital video data comprises metadata describing the set of objects. A size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object. The set of size and shape 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 size and shape based attribute in common.

Claims

1. A computer implemented method for generating cohorts using size and shape attributes of objects, the computer implemented method comprising:

processing digital video data, by a video analysis engine, to identify a set of size and shape based attributes associated with a set of objects, wherein the digital video data comprises metadata describing the set of objects, and wherein a size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object;

analyzing the set of size and shape based attributes using cohort criteria to form a result, wherein the cohort criteria specify attributes that are associated with members of a given cohort;

generating 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 size and shape based attribute in common;

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 processes 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 of the set of video based cohorts.

2. The computer implemented method of claim 1, wherein the size and shape attributes comprises an identification of a length of the portion of the object in the set of objects.

3. The computer implemented method of claim 1, wherein the size and shape attributes comprises a height of the portion of the object in the set of objects.

4. The computer implemented method of claim 1, wherein the size and shape attributes comprises a length of the portion of the object in the set of objects.

5. The computer implemented method of claim 1, wherein the subset of objects from the set of objects that share at least one size and shape based attributes are vehicles, and wherein the computer implemented method further comprises:

processing the set of video based cohorts by the inference engine to determine how many vehicles of a particular size will be driven in a particular region at a future time.

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

calculating, based on the size and shape attributes of an object in the set of objects, an estimated volume of the object in the set of objects, wherein the estimated volume is calculated based on a height, length, width, and radius of the object in the set of objects; and

calculating an estimated weight o the object in the set of objects based on the estimated volume and a known density of the object in the set of objects.

7. The computer implemented method of claim 1, wherein the size and shape attributes comprises size and shape based identification markings associated with the portion of the object in the set of objects, and wherein the computer implemented method further comprising:

parsing the size and shape based identification markings to identify the object; and

checking a lookup table to determine a weight or volume of the object based on the identification of the object.

8. The computer implemented method of claim 7, wherein the identification markings comprises at least one of a license plate number, a label on the object, a serial number, a bar code, a lot number, a model number, and a product name.

9. The computer implemented method of claim 1, wherein the digital video data is received from a set of video cameras.

10. The computer implemented method of claim 1 wherein analyzing the set of size and shape based attributes using the cohort criteria to form the result further comprises:

analyzing the size and shape based attributes using a set of size and shape patterns, by a cohort generation engine, to form the result.

11. The computer implemented method of claim 1, wherein analyzing the set of size and shape based attributes using the cohort criteria to form the result further comprises:

analyzing the size and shape based attributes using cohort constraints to form the result, wherein cohort constraints specify attributes that are absent from members of a given cohort in the set of video based cohorts.

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

a non-transitory computer readable storage medium having computer usable program code embodied therewith, the computer usable program code comprising;

computer usable program code configured to process digital video data, by a video analysis engine, to identify a set of size and shape based attributes associated with the set of objects, wherein the digital video data comprises metadata describing the set of objects, and wherein a size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object;

computer usable program code configured to analyze the set of size and shape based attributes using cohort criteria to form a result, wherein the cohort criteria specify attributes that are associated with members of a given cohort;

computer usable program code configured to generate a set of video 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 size and shape based attribute in common;

a computer usable program code configured to calculate, based on the size and shape attribute of the object in the set of objects, and estimated volume of the object in the set of objects wherein the estimated volume is calculated based on a height, length, width, and radius of the object in the set of objects; and

p1 a computer usable program code configured to calculate an estimated weight of the object in the set of objects based on the estimated volume and a known density of the object in the set of objects.

13. The computer program product of claim 12, wherein the size and shape attributes comprise an identification of a height of the portion of the object in the set of objects.

14. The computer program product of claim 12, wherein the size and shape attributes comprise an identification of a length of the portion of the object in the set of objects.

15. The computer program product of claim 12, wherein the size and shape attributes comprise an identification of a width of the portion of the object in the set of objects.

16. The computer program product of claim 12, wherein the objects from the set of objects that share at least one size and shape based attribute are vehicles, and wherein the computer program product further comprises:

computer usable program code configured to process the set of video based cohorts by the inference engine to determine how many vehicles of a particular size will be in a particular region at a predefined future time.

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

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

computer usable program code configured 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.

18. 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 size and shape based attributes associated with the set of objects, wherein the digital video data is received from a set of video cameras, wherein the digital video data comprises metadata describing the set of objects, and wherein a size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object;

analyze the set of size and shape based attributes using cohort criteria to form a result, wherein the cohort criteria specify attributes that are associated with members of a given cohort; and

generate 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 size and shape based attribute in common;

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 processes the set of video based cohorts to generate a set of inferences, and wherein the set of inferences predicts a future activity by members described by the set of video based cohorts.

19. The apparatus of 18, 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.

20. A video cohort generation system comprising:

a set of cameras, wherein the set of cameras captures a set of images of a plurality of objects;

a digital video analysis engine, wherein the digital video analysis engine processes digital video data, by a video analysis engine, to identify a set of size and shape based attributes associated with the plurality of objects, wherein the digital video data comprises metadata describing the plurality of objects, and wherein a size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object;

a cohort generation engine, wherein the cohort generation engine analyzes the set of size and shape based attributes using cohort criteria to form a result, wherein the cohort criteria specify attributes that are associated with members of a given cohort; and

generates a set of cohorts based on the result, wherein each cohort in the set of cohorts comprises a subset of objects from the plurality of objects that share at least one size and shape based attribute in common; and

an inference engine, wherein the inference engine processes the set of cohorts to generate a set of inferences, and wherein the set of inferences identifies a predicted future activity by members of the set of cohorts.