Non-linear associator and motion discriminator

• US 9,870,620 B2
• Filed: 04/12/2016
• Issued: 01/16/2018
• Est. Priority Date: 06/18/2015
• Status: Active Grant

• Current Assignee: Johns Hopkins University
• Original Assignee: Johns Hopkins University
• Inventors: Pavek, Richard E., Hughes, Alexander S.
• Primary Examiner(s): Chang, Jon
• Application Number:
  US15/096,311
• Publication Number:
  US 20160371849A1
• Time in Patent Office: 644 Days
• CPC Class Codes: G01S 13/52 Discriminating between fixed and moving objects or between objects moving at different speeds
• CPC Class Codes: G01S 7/414 Discriminating targets with respect to background clutter
• CPC Class Codes: G06T 2207/10044 Radar image
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]

Abstract

An image analyzer includes processing circuitry that receives at least one image having a first set of bins and a second set of bins, shifts the first or second set of bins by a number of bins associated with a motion hypothesis to achieve sets of aligned bins, determines a product for each set of aligned bins, compares the products to a product threshold, and identifies an object based on the products that exceed the product threshold.

Claims

1. An image analyzer comprising processing circuitry and computer product code configured to:

receive at least one image associated with a first set of bins and a second set of bins;

shift the first or second sets of bins by a number of bins associated with a motion hypothesis to achieve sets of aligned bins;

determine products for each set of aligned bins;

compare the products to a product threshold; and

identify an object based on the products that exceed the product threshold.

2. The image analyzer of claim 1, wherein bins associated with a product that fails to exceed the product threshold are set to zero.

3. The image analyzer of claim 1, wherein the processing circuitry is further configured to:

receive a third set of bins;

shift the products of the aligned bins by the number of bins associated with the motion hypothesis to achieve second sets of aligned bins;

determine second products of each of the aligned bins of the second sets of aligned bins;

compare the second products to a second product threshold; and

determine the object based on the second products that exceed the second product threshold.

4. The image analyzer of claim 3, wherein the processing circuitry is further configured to:

identify an object track based on the identified object.

5. The image analyzer of claim 3, wherein the identified object occupies a group of one or more associated bins.

6. The image analyzer of claim 1, wherein the processing circuitry is further configured to:

compare the first and second sets of bins to a detection threshold; and

set bins that fail to exceed the detection threshold to zero.

7. The image analyzer of claim 6, wherein the product threshold is the detection threshold squared.

8. The image analyzer of claim 7, wherein the processing circuitry is further configured to:

receive a third set of bins;

shift the aligned bins by the number of bins associated with the motion hypothesis to achieve second sets of aligned bins;

determine second product of each of the aligned bins of the second sets of aligned bins;

compare the second products to a second product threshold; and

identify the object based on the second products that exceed the second product threshold,

wherein the second product threshold comprises the detection threshold cubed.

9. The image analyzer of claim 1, wherein the motion hypothesis is based on an object velocity.

10. The image analyzer of claim 1, wherein the processing circuitry is further configured to:

align the at least one image based on the motion hypothesis.

11. An image analyzer system comprising:

a sensor configured to capture images; and

an image analyzer comprising processing circuitry configured to;

receive at least one image associated with a first set of bins and a second set of bins;

shift the first or second sets of bins by a number of bins associated with a motion hypothesis to achieve sets of aligned bins;

determine products for each set of aligned bins;

compare the products to product threshold; and

identify an object based on the products that exceed the product threshold.

12. The image analyzer of claim 11, wherein bins associated with a product that fails to exceed the product threshold are set to zero.

13. The image analyzer of claim 11, wherein the processing circuitry is further configured to:

receive a third set of bins;

shift the products of the aligned bins by the number of bins associated with the motion hypothesis to achieve second sets of aligned bins;

determine second product of each of the aligned bins of the second set of aligned bins;

compare the second products to a second product threshold; and

identify a second object based on the second products that exceed the second product threshold.

14. The image analyzer of claim 13, wherein the processing circuitry is further configured to:

identify an object track based on the identified object.

15. The image analyzer of claim 13, wherein the identified object occupies a group of one or more associated bins.

16. The image analyzer of claim 11, wherein the processing circuitry is further configured to:

compare the first and second sets of bins to a detection threshold; and

set bins which fail to exceed the detection threshold to zero.

17. The image analyzer of claim 16, wherein the product threshold is the detection threshold squared.

18. The image analyzer of claim 17, wherein the processing circuitry is further configured to:

receive a third set of bins;

shift the products of the aligned bins by the number of bins associated with the motion hypothesis to achieve second sets of aligned bins;

determine second product of each of the aligned bins of the second sets of aligned bins;

compare the second product to a second product threshold; and

identify the object based on the second products that exceed the second product threshold,

wherein the second product threshold comprises the detection threshold cubed.

19. The image analyzer of claim 11, wherein the motion hypothesis is based on an object velocity.

20. The image analyzer of claim 11, wherein the processing circuitry is further configured to:

align the at least one image based on the motion hypothesis.