CALIBRATION OF VIDEO OBJECT CLASSIFICATION

• US 20130251275A1
• Filed: 05/20/2013
• Published: 09/26/2013
• Est. Priority Date: 08/28/2008
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Brown, Lisa Marie, Chen, Longbin, Feris, Rogerio Schmidt, Hampapur, Arun, Zhai, Yun
• Granted Patent: US 8,774,532 B2
• Time in Patent Office: Days
• US Class Current: 382/224
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/235 based on user input or interaction
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04W 4/02 Services making use of location information

Abstract

Techniques for calibrating a classification system, wherein one or more objects in at least one video are classified, are provided. At least one view associated with the at least one video is obtained. The at least one view is partitioned into at least one region. A given object is classified in accordance with its location in reference to the at least one region. In an additional embodiment, one or more object models are obtained. At least one normalized size of the one or more objects is defined within at least one view associated with the at least one video in accordance with the one or more object models. The one or more objects are classified in accordance with the at least one defined normalized size.

Claims

1. A method for calibrating a classification system, wherein one or more objects in at least one video are classified, the method comprising:

obtaining one or more object models; and

defining at least one normalized size of the one or more objects within at least one view associated with the at least one video in accordance with the one or more object models, such that the one or more objects are classified in accordance with the at least one defined normalized size;

wherein the one or more object models are obtained via a user specifying one or more object size samples within the at least one view such that each of the one or more object models respectively corresponds to each of the one or more user-specified object size samples, and further wherein a predicted size distribution for at least a portion of the at least one view is computed by interpolating the one or more user-specified object size samples.

2. The method of claim 1, further comprising approximating an expected size of the one or more objects for one or more locations within the at least one view in accordance with the at least one defined normalized size.

3. The method of claim 1, further comprising determining a probability that a given object belongs to a specific class, such that the probability is in accordance with a size of the given object, a location of the given object, and an expected size of the given object at a given location within the at least one view.

4. The method of claim 3, wherein the given object is classified in accordance with the determined probability in combination with at least one of a probability based on a velocity of the given object and a probability based on a level of deformation of the given object.

5. A computer program product for calibrating a classification system, wherein one or more objects in at least one video are classified, the computer program product comprising a computer-readable non-transitory storage medium including one or more programs, which when executed by a computer implement the steps of:

obtaining one or more object models; and

defining at least one normalized size of the one or more objects within at least one view associated with the at least one video in accordance with the one or more object models, such that the one or more objects are classified in accordance with the at least one defined normalized size;

wherein the one or more object models are obtained via a user specifying one or more object size samples within the at least one view such that each of the one or more object models respectively corresponds to each of the one or more user-specified object size samples, and further wherein a predicted size distribution for at least a portion of the at least one view is computed by interpolating the one or more user-specified object size samples.

6. The computer program product of claim 5, further comprising the step of approximating an expected size of the one or more objects for one or more locations within the at least one view in accordance with the at least one defined normalized size.

7. The computer program product of claim 5, further comprising the step of determining a probability that a given object belongs to a specific class, such that the probability is in accordance with a size of the given object, a location of the given object, and an expected size of the given object at a given location within the at least one view.

8. The computer program product of claim 5, wherein the given object is classified in accordance with the determined probability in combination with at least one of a probability based on a velocity of the given object and a probability based on a level of deformation of the given object.

9. An apparatus for calibrating a classification system, wherein one or more objects in at least one video are classified, the apparatus comprising:

a memory; and

at least one processor coupled to the memory and operative to;

obtain one or more object models; and

define at least one normalized size of the one or more objects within at least one view associated with the at least one video in accordance with the one or more object models, such that the one or more objects are classified in accordance with the at least one defined normalized size;

wherein the one or more object models are obtained via a user specifying one or more object size samples within the at least one view such that each of the one or more object models respectively corresponds to each of the one or more user-specified object size samples, and further wherein a predicted size distribution for at least a portion of the at least one view is computed by interpolating the one or more user-specified object size samples.

10. The apparatus of claim 9, wherein the at least one processor is further operative to approximate an expected size of the one or more objects for one or more locations within the at least one view in accordance with the at least one defined normalized size.

11. The apparatus of claim 9, wherein the at least one processor is further operative to determine a probability that a given object belongs to a specific class, such that the probability is in accordance with a size of the given object, a location of the given object, and an expected size of the given object at a given location within the at least one view.

12. The apparatus of claim 11, wherein the given object is classified in accordance with the determined probability in combination with at least one of a probability based on a velocity of the given object and a probability based on a level of deformation of the given object.