Automated object classification using temperature profiles

• US 9,310,252 B2
• Filed: 09/13/2012
• Issued: 04/12/2016
• Est. Priority Date: 05/18/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Das, Rajarshi, Isci, Canturk, Kephart, Jeffrey O., Lenchner, Jonathan
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): PELLETT, DANIEL T
• Application Number:
  US13/613,270
• Publication Number:
  US 20130311407A1
• Time in Patent Office: 1,307 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01J 5/0003 for sensing the radiant heat transfer of samples, e.g. emittance meter
• CPC Class Codes: G01J 5/485 Temperature profile
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

Methods and apparatus are provided for automated object classification using temperature profiles. An object in an environment (such as an exemplary data center) is classified by obtaining a surface temperature profile of the object; and classifying the object as a particular type of equipment based on the obtained surface temperature profile. The surface temperature profile of the object can be compared to a plurality of predefined characteristic surface temperature profiles each associated with a given type of equipment.

Claims

1. A method for classifying an object in an environment, comprising:

obtaining a surface temperature profile for a plurality of surface points of said object in an operational mode;

evaluating a physical extent of said object;

classifying said object as a part of a structure of said environment if said object extends from a floor to a ceiling in said environment; and

if said object does not extend from said floor to said ceiling in said environment, classifying said object as a particular type of one or more of information technology equipment and facilities equipment based on said obtained surface temperature profile for said plurality of surface points of said object in an operational mode and said physical extent, wherein said classifying step is performed by at least one hardware device.

2. The method of claim 1, further comprising the step of comparing said surface temperature profile of said object to a plurality of predefined characteristic surface temperature profiles each associated with a given type of equipment.

3. The method of claim 2, wherein said predefined characteristic surface temperature profiles are stored as one or more of rules and feature vectors.

4. The method of claim 2, wherein said predefined characteristic surface temperature profiles evaluate temperature characteristics of said object.

5. The method of claim 4, wherein said temperature characteristics of said object comprise a temperature of said object at one or more air inlets.

6. The method of claim 2, wherein said predefined characteristic surface temperature profiles compare a surface temperature of said object to an air temperature.

7. The method of claim 2, wherein said predefined characteristic surface temperature profiles evaluate an approximate height populated with equipment that is powered on.

8. The method of claim 1, further comprising the step of determining a location of said object.

9. The method of claim 8, wherein said location of said object is determined using a Simultaneous Localization and Mapping system.

10. The method of claim 1, wherein said surface temperature profile of said object is obtained using a robot having at least one temperature measuring device.

11. The method of claim 10, wherein said robot further comprises a location sensing capability.

12. The method of claim 1, wherein said surface temperature profile of said object is obtained using a plurality of infrared imaging devices.

13. The method of claim 1, wherein said environment comprises a manufacturing environment.

14. The method of claim 2, wherein said plurality of predefined characteristic surface temperature profiles associated with a given type of equipment is learned over time using human-labeled examples.