System and method for employing an object-oriented motion detector to capture images

• US 7,403,640 B2
• Filed: 04/29/2004
• Issued: 07/22/2008
• Est. Priority Date: 10/27/2003
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Safai, Fereydoon, Zhang, Bin
• Primary Examiner(s): Johns; Andrew W.
• Assistant Examiner(s): Allison; Andrae S
• Application Number:
  US10/834,589
• Publication Number:
  US 20050091267A1
• Time in Patent Office: 1,545 Days
• Field of Search: 382/107, 382/103, 348/207.1, 348/208.99, 348/120, 707/101
• US Class Current: 382/107
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/90 Details of database functions independent of the retrieved data types
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions

Abstract

The disclosure relates to a system having an image capturing device and an object-oriented motion detector with a motion analysis algorithm that detects motion of a subject and signals the image capturing device responsive to the motion of the subject.

Claims

1. A system, comprising:

an image capturing device; and

an object-oriented motion detector having a regression clustering algorithm configured for motion analysis, the object-oriented motion detector being configured to detect motion of a subject and signal the image capturing device responsive to the motion of the subject, wherein the regression clustering algorithm comprises a K-Harmonic Mean regression algorithm and a K-Harmonic Mean performance function.

2. The system of claim 1, wherein the motion analysis algorithm signals the image capturing device to record an image.

3. The system of claim 1, comprising:

an automatic mode that enables automatic activation of the image capturing device based on a motion extreme.

4. A method for automatically capturing an image, comprising:

performing a motion analysis on image data with a K-Harmonic Mean regression algorithm and a K-Harmonic Mean performance function, comprising;

determining distances between data points of a dataset and values correlated with a set number of functions;

regressing the set number of functions using data point membership probability and weighting factors associated with the determined distances;

calculating a difference value associated with the distances determined prior to and subsequent to the regressing;

repeating the regressing, determining, and calculating upon determining the difference value is greater than a predetermined value;

defining an object; and

capturing the image based on a motion path estimation.

5. The method of claim 4, comprising:

determining distances from each data point of the dataset to values within each function of the set number of functions.

6. The method of claim 4, wherein the difference value comprises a change between repeat calculations in the data point membership probabilities.

7. The method of claim 4, wherein the difference value is a change between repeat calculations in the set number of functions, wherein the set number of functions comprise K functions.

8. The method of claim 4, comprising:

applying a regression algorithm and an Expectation Maximization performance function on the dataset.

9. A system for automatically capturing an image, comprising:

a determining module that determines distances between data points of a dataset and values correlated with a set number of functions;

a regression module that regresses the set number of functions using data point membership probability and weighting factors associated with the determined distances, wherein the regression module comprises a K-Harmonic Mean performance function that is configured to function as a regression clustering algorithm;

a calculation module that calculates a difference value associated with the distances determined prior to and subsequent to the regressing;

an iteration module that facilitates repetition of the regressing, determining, and calculating of the regression module, the determining module, and the calculation module upon determining the difference value is greater than a predetermined value;

a defining module that defines an object; and

an image capture module that captures the image based on a motion path estimation.

10. The system of claim 9, comprising:

a second determining module for determining distances from each data point of the dataset to values within each function of the set number of functions.

11. The system of claim 9, wherein the difference value comprises a change between repeat calculations in the data point membership probabilities.

12. The system of claim 9, wherein the difference value is a change between repeat calculations in the set number of functions, wherein the set number of functions comprise K functions.

13. The system of claim 9, comprising:

a regression and expectation maximization module that applies a regression algorithm and an Expectation Maximization performance function on the dataset.

14. A computer readable storage medium storing a computer program product tangibly embodying program instructions executable by a processor, the program instructions, comprising:

a determining module stored on the computer-readable medium, the determining module adapted to determine distances between data points of a dataset and values correlated with a set number of functions;

a regression module stored on the computer-readable medium, the regression module adapted to regress the set number of functions using data point membership probability and weighting factors associated with the determined distances, wherein the regression module comprises a K-Harmonic Mean performance function that is configured to function as a regression clustering algorithm;

a calculation module stored on the computer-readable medium, the calculation module adapted to calculate a difference value associated with the distances determined prior to and subsequent to the regressing;

an iteration module stored on the computer-readable medium, the iteration module adapted to facilitate repetition of the regressing, determining, and calculating of the regression module, the determining module, and the calculation module upon determining the difference value is greater than a predetermined value;

a defining module stored on the computer-readable medium, the defining module adapted to define an object; and

an image capture module stored on the computer-readable medium, the image capture module adapted to capture the image based on a motion path estimation.

15. The program of claim 14, comprising:

a regression and expectation maximization module stored on the computer-readable medium, the regression and expectation maximization module adapted to apply a regression algorithm and an Expectation Maximization performance function on the dataset.

16. An automatic image capturing system, comprising:

means for performing a motion analysis on image data with a K-Harmonic Mean regression algorithm and a K-Harmonic Mean performance function, comprising;

means for determining distances between data points of a dataset and values correlated with a set number of functions;

means for regressing the set number of functions using data point membership probability and weighting factors associated with the determined distances;

means for calculating a difference value associated with the distances determined prior to and subsequent to the regressing;

means for facilitating repeating the regressing, determining, and calculating upon determining the difference value is greater than a predetermined value;

means for defining an object; and

means for capturing the image based on a motion path estimation.