APPARATUS AND METHOD FOR OBJECT CONFIRMATION AND TRACKING

• US 20120084091A1
• Filed: 10/05/2010
• Published: 04/05/2012
• Est. Priority Date: 10/05/2010
• Status: Active Grant

• Current Assignee: AI Cure Technologies LLC
• Original Assignee: AI Cure Technologies LLC
• Inventors: Hanina, Adam, Kessler, Gordon, Guan, Lei
• Granted Patent: US 10,762,172 B2
• Time in Patent Office: Days
• US Class Current: 705/2
• CPC Class Codes: G06Q 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/80 Recognising image objects characterised by unique random patterns
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 70/40 relating to drugs, e.g. their side effects or intended usage

Abstract

A method and apparatus for tracking a medication to be administered by a user. The method includes the steps of determining the identity of a medication to be administered by a user, identifying one or more characteristics associated with the medication that are to be used to continue to track the medication, the one or more characteristics including less than a total number of characteristics associated with the medication to be administered, and tracking the medication to be administered in accordance with the identified one or more characteristics through one or more future video images.

Claims

1. A method for tracking a medication to be administered by a user, comprising the steps of:

determining the identity of a medication to be administered by a user;

identifying one or more tracking characteristics associated with the medication that are to be used to continue to track the medication, the one or more tracking characteristics comprising less than a total number of characteristics associated with the medication to be administered; and

tracking the medication to be administered in accordance with the identified one or more tracking characteristics through one or more future video images.

2. The method of claim 1, wherein the step of determining the identity of the medication to be administered by the user further comprises the steps of:

capturing a plurality of video images of the medication;

determining one or more values of one or more characteristics associated with the medication from the captured plurality of video images;

comparing the determined one or more values to predetermined thresholds for the one or more characteristics; and

confirming the identity of the medication when a sufficient number of values of the one or more characteristics of the medication pass the thresholds.

3. The method of claim 2, further comprising the step of determining the one or more tracking characteristics to be used to continue to track the medication from the total number of characteristics associated with the medication.

4. The method of claim 1, wherein the step of determining the identity of the medication to be administered by the user further comprises the step of imaging the identity from one or more indicators contained on a medication container.

5. The method of claim 1, wherein the medication to be administered by the user is one of a predetermined number of medications that may be administered by the user.

6. The method of claim 5, wherein the step of determining the identity of the medication to be administered by the user further comprises the steps of:

capturing a plurality of video images of the medication;

determining one or more values of one or more characteristics associated with the medication from the captured plurality of video images to generate a characteristic fingerprint of the medication;

comparing the generated characteristic fingerprint to one or more predetermined characteristic fingerprint models associated with each of the predetermined number of medications; and

confirming the identity of the medication by selecting a medication associated with the fingerprint model determined to be a closest match to the generated characteristic fingerprint.

7. The method of claim 6, further comprising the step of generating one or more super resolution images from the plurality of video images;

wherein the generated characteristic fingerprint is generated from the one or more super resolution images.

8. The method of claim 6, further comprising the steps of:

sampling one or more of the plurality of video images to reduce the resolution thereof to generate one or more low resolution images;

wherein the determining one or more values of one or more characteristics associated with the medication is performed on the sampled, low resolution image versions of the captured plurality of video images to generate a characteristic fingerprint of the medication; and

wherein confirming the identity of the medication is performed by selecting one or more medications associated with the fingerprint models determined to be a sufficiently close match to the generated characteristic fingerprint to form a potential group of medications.

9. The method of claim 8, further comprising the steps of:

sampling one or more of the plurality of video images to reduce the resolution thereof to generate one or more medium resolution images having a resolution higher than the low resolution images;

wherein the determining one or more values of one or more characteristics associated with the medication is performed on the sampled, medium resolution versions of the captured plurality of video images to generate a second characteristic fingerprint of the medication; and

wherein confirming the identity of the medication is performed by selecting one or more medications from the group of potential medications associated with the fingerprint models determined to be a sufficiently close match to the generated second characteristic fingerprint.

10. An apparatus for tracking a medication to be administered by a user, comprising:

an image capture apparatus for capturing one or more images of a medication to be administered by a user; and

a processor for determining the identity of a medication to be administered by a user, identifying one or more tracking characteristics associated with the medication that are to be used to continue to track the medication, the one or more tracking characteristics comprising less than a total number of characteristics associated with the medication to be administered, and tracking the medication to be administered in accordance with the identified one or more tracking characteristics through one or more future video images captured by the image capture apparatus.

11. The apparatus of claim 10, wherein the processor further determines one or more values of one or more characteristics associated with the medication from the captured one or more video images, compares the determined one or more values to predetermined thresholds for the one or more characteristics, and confirms the identity of the medication when a sufficient number of values of the one or more characteristics of the medication pass the thresholds.

12. The apparatus of claim 11, wherein the processor determines one or more tracking characteristics to be used to continue to track the medication from the total number of characteristics associated with the medication.

13. The apparatus of claim 10, wherein the image capture apparatus captures one or more images of a medication container associated with the medication to be administered, and the processor further determines the identity of the medication to be administered by the user from one or more indicators contained on the medication container.

14. The apparatus of claim 10, wherein the medication to be administered by the user is one of a predetermined number of medications that may be administered by the user.

15. The method of claim 14, wherein the processor further determines one or more values of one or more characteristics associated with the medication from the captured plurality of video images to generate a characteristic fingerprint of the medication, compares the generated characteristic fingerprint to one or more predetermined characteristic fingerprint models associated with each of the predetermined number of medications, and confirms the identity of the medication by selecting a medication associated with the fingerprint model determined to be a closest match to the generated characteristic fingerprint.

16. The method of claim 15, wherein the processor further generates one or more super resolution images from the plurality of video images, and wherein the generated characteristic fingerprint is generated from the one or more super resolution images.

17. The method of claim 15, wherein the processor further samples one or more of the plurality of video images to reduce the resolution thereof to generate one or more low resolution images, determines the one or more values of one or more characteristics associated with the medication from the sampled, low resolution image versions of the captured plurality of video images to generate a characteristic fingerprint of the medication, and confirms the identity of the medication by selecting one or more medications associated with the fingerprint models determined to be a sufficiently close match to the generated characteristic fingerprint to form a potential group of medications.

18. The method of claim 17, wherein the processor further samples one or more of the plurality of video images to reduce the resolution thereof to generate one or more medium resolution images having a resolution higher than the low resolution images, determines one or more values of one or more characteristics associated with the medication from the sampled, medium resolution versions of the captured plurality of video images to generate a second characteristic fingerprint of the medication, and confirms the likeness of the medication by selecting one or more medications from the group of potential medications associated with the fingerprint models determined to be a sufficiently close match to the second generated characteristic fingerprint.

19. A computer program for tracking a medication to be administered by a user stored to a computer readable medium and operable on a computing device, the computer program causing the computing device to perform the steps of:

determining the identity of a medication to be administered by a user;

identifying one or more tracking characteristics associated with the medication that are to be used to continue to track the medication, the one or more tracking characteristics comprising less than a total number of characteristics associated with the medication to be administered; and

tracking the medication to be administered in accordance with the identified one or more tracking characteristics through one or more future video images.

20. The computer program of claim 19, wherein the step of determining the identity of the medication to be administered by the user further comprises the steps of:

capturing a plurality of video images of the medication;

determining one or more values of one or more characteristics associated with the medication from the captured plurality of video images;

comparing the determined one or more values to predetermined thresholds for the one or more characteristics; and

confirming the identity of the medication when a sufficient number of values of the one or more characteristics of the medication pass the thresholds.

21. The computer program of claim 20, further comprising the step of determining the one or more tracking characteristics to be used to continue to track the medication from the total number of characteristics associated with the medication.

22. The computer program of claim 19, wherein the step of determining the identity of the medication to be administered by the user further comprises the step of imaging the identity from one or more indicators contained on a medication container.

23. The computer program of claim 19, wherein the medication to be administered by the user is one of a predetermined number of medications that may be administered by the user.

24. The computer program of claim 23, wherein the step of determining the identity of the medication to be administered by the user further comprises the steps of:

capturing a plurality of video images of the medication;

determining one or more values of one or more characteristics associated with the medication from the captured plurality of video images to generate a characteristic fingerprint of the medication;

comparing the generated characteristic fingerprint to one or more predetermined characteristic fingerprint models associated with each of the predetermined number of medications; and

confirming the identity of the medication by selecting a medication associated with the fingerprint model determined to be a closest match to the generated characteristic fingerprint.

25. The computer program of claim 24, further comprising the step of generating one or more super resolution images from the plurality of video images;

wherein the generated characteristic fingerprint is generated from the one or more super resolution images.

26. The computer program of claim 24, further comprising the steps of:

sampling one or more of the plurality of video images to reduce the resolution thereof to generate one or more low resolution images;

wherein the determining one or more values of one or more characteristics associated with the medication is performed on the sampled, low resolution image versions of the captured plurality of video images to generate a characteristic fingerprint of the medication; and

wherein confirming the identity of the medication is performed by selecting one or more medications associated with the fingerprint models determined to be a sufficiently close match to the generated characteristic fingerprint to form a potential group of medications.

27. The computer program of claim 26, further comprising the steps of:

sampling one or more of the plurality of video images to reduce the resolution thereof to generate one or more medium resolution images having a resolution higher than the low resolution images;

wherein the determining one or more values of one or more characteristics associated with the medication is performed on the sampled, medium resolution versions of the captured plurality of video images to generate a second characteristic fingerprint of the medication; and

wherein confirming the identity of the medication is performed by selecting one or more medications from the group of potential medications associated with the fingerprint models determined to be a sufficiently close match to the generated second characteristic fingerprint.