Flow meter using a dynamic background image

• US 9,759,343 B2
• Filed: 11/11/2015
• Issued: 09/12/2017
• Est. Priority Date: 12/21/2012
• Status: Active Grant

• Current Assignee: Deka Products Limited Partnership
• Original Assignee: Deka Products Limited Partnership
• Inventors: Peret, Bob D., Kane, Derek G., Kamen, Dean, Murphy, Colin H., Kerwin, John M.
• Primary Examiner(s): Pontius, James
• Application Number:
  US14/938,083
• Publication Number:
  US 20160073063A1
• Time in Patent Office: 671 Days
• CPC Class Codes: A61M 2205/3306 Optical measuring means
• CPC Class Codes: A61M 2205/3334 Measuring or controlling the flow rate
• CPC Class Codes: A61M 2205/50 with microprocessors or computers
• CPC Class Codes: A61M 39/284 Lever clamps
• CPC Class Codes: A61M 5/1411 Drip chambers A61M5/162, A61M5/1689, A61M5/40 take precedence
• CPC Class Codes: A61M 5/16804 Flow controllers
• CPC Class Codes: A61M 5/16877 Adjusting flow; Devices for setting a flow rate
• CPC Class Codes: A61M 5/16886 for measuring fluid flow rate, i.e. flowmeters
• CPC Class Codes: A61M 5/1689 Drip counters
• CPC Class Codes: A61M 5/172 electrical or electronic A61M5/16804, A61M5/16831 take precedence
• CPC Class Codes: F16K 27/00 Construction of housing methods for welding housings B23K; Use of materials therefor
• CPC Class Codes: G01F 1/661 using light
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05D 7/0635 by action on throttling means G05D7/0688, G05D7/0694 take precedence
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/20182 Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 5/50 : using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/70 : Denoising; Smoothing
• CPC Class Codes: G06T 7/0012 : Biomedical image inspection
• 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 7/60 : Analysis of geometric attributes
• CPC Class Codes: G06V 10/141 : Control of illumination
• CPC Class Codes: G06V 10/30 : Noise filtering
• CPC Class Codes: G06V 10/75 : Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 10/761 : Proximity, similarity or dissimilarity measures
• CPC Class Codes: H04N 7/183 : for receiving images from a single remote source

Abstract

A flow meter includes a coupler, a support member, an image sensor, and one or more processors. The coupler is adapted to couple to a drip chamber. The support member is coupled to the coupler. The image sensor has a field of view and is operatively coupled to the support member. The image sensor is positioned to view the drip chamber within the field of view. The processor is operatively coupled to the image sensor to receive image data from the image sensor and is configured to: capture an image of a drip chamber using an image sensor; compare the image of a drip chamber with a dynamic background image; and adjust a flow rate of fluid flowing through the fluid line in accordance with the comparison between the image of the drip chamber and the dynamic background image.

Claims

1. A method for adjusting a flow rate of a fluid line, the method comprising:

capturing an image of a drip chamber using an image sensor;

comparing the image of a drip chamber with a dynamic background image wherein the dynamic background image contains a pattern having a plurality of lines; and

adjusting a flow rate of fluid flowing through the fluid line in accordance with the comparison between the image of the drip chamber and the dynamic background image.

2. The method according to claim 1, wherein the dynamic background image is generated using another image captured by the image sensor.

3. The method according to claim 1, further comprising the act of estimating a volume of the drop using the comparison between the image of the drip chamber and the dynamic background image.

4. The method according to claim 1, further comprising the act of identifying a plurality of pixels of interest within the image.

5. The method according to claim 4, wherein the plurality of pixels of interest are identified by comparing the image to the dynamic background image.

6. The method according to claim 4, further comprising the act of determining a subset of pixels within the plurality of pixels of interest, wherein each pixel of the plurality of pixels is determined to be within the subset of pixels when there is a path to a baseline corresponding to the drip chamber.

7. The method according to claim 4, further comprising the act of determining a volume of the drop based upon the plurality of pixels of interest.

8. The method according to claim 1, further comprising the act of initializing the dynamic background image.

9. The method according to claim 1, further comprising the act of updating the dynamic background image using the image captured by the image sensor.

10. The method according to claim 9, wherein the dynamic background image is updated in accordance with:

P_{background,i,j}=P_{background,i,j}(1−

α

_background)+α

_backgroundP_input,i,j.

11. The method as in claim 1, further comprising the act of updating an array of variances using the image captured by the image sensor.

12. The method according to claim 11, wherein the array of variances is updated in accordance with:

σ

_temp²=(P_{background,i,j}−

P_input,i,j)²

σ

_{background,i,j}²=σ

_{background,i,j}²(1−

β

_background)+β

_backgroundσ

_temp².

13. The method according to claim 1, further comprising the act of updating an array of integers in accordance with the image captured by the image sensor.

14. The method according to claim 13, wherein each integer of the array of integers corresponds to a number of updates of a pixel of the dynamic background image.

15. The method according to claim 14, wherein the comparison of the image to the dynamic background image only compares pixels within the image to pixels within the dynamic background image if a respective integer of the array of integers indicates a respective pixel within the dynamic background image has been updated at least a predetermined number of times.

16. The method according to claim 1, further comprising the acts of:

identifying a drop in the image and a predetermined band near an edge of the drop; and

initializing the dynamic background image by setting each pixel of the dynamic background image to the image unless it is within the identified drop or the predetermined band near the edge of the drop.

17. The method according to claim 16, further comprising the act of setting a pixel of the dynamic background image to a predetermined value if a corresponding pixel of the image is within the identified drop or the predetermined band near the edge of the drop.

18. The method according to claim 17, wherein the corresponding pixel of the image has a location corresponding to a location of the pixel of the dynamic background image.

19. The method according to claim 1, further comprising the act of determining the baseline corresponding to an opening of the drip chamber.

20. The method according to claim 1, wherein the act of determining a subset of pixels within the plurality of pixels of interest that corresponds to a drop includes determining each of the plurality of pixels of interest is within the subset of pixels if the respective pixel of the plurality of pixels has a contiguous path back to the baseline of the drop forming at an opening of the drip chamber.

21. The method according to claim 1, further comprising the acts of:

identifying the drop within the image and a predetermined band near an edge of the drop;

initializing the dynamic background image by setting each pixel to the image unless it is within the identified drop or the predetermined band near the edge of the drop;

setting pixels within the region of the drop or within the predetermined band to a predetermined value;

initializing an array of integers; and

initializing an array of variances.

22. The method according to claim 21, further comprising the act of updating the dynamic background image, the array of integers, and the array of variances using the image.

23. The method according to claim 1, further comprising the act of adjusting a valve to control the flow rate.

24. The method according to claim 1, wherein the dynamic background image is configured to filter out low frequency artifacts.

25. The method according to claim 1, further comprising the acts of:

subtracting the image from the dynamic background image to thereby generate a difference image;

converting each pixel of the difference image to a true value if an absolute value of a respective pixel is beyond a predetermined threshold or to a false value if the absolute value of the respective pixel is less than the predetermined threshold;

summing each row of the converted difference image to generate a plurality of summation values, wherein each summation value of the plurality of summation values corresponds to a respective row of the converted difference image; and

examining the plurality of summation values.

26. The method according to claim 25, wherein the act of examining the plurality of summation values includes determining if a free flow condition exists within the drip chamber.

27. The method according to claim 25, wherein the act of examining the plurality of summation values includes determining if the free flow condition by determining if the plurality of summation values includes a plurality of contiguous summation values above another predetermined threshold.

28. The method according to claim 25, wherein act of examining the plurality of summation values includes determining if a drop has been formed within the drip chamber.

29. The method according to claim 28, wherein the act of determining if the drop has been formed within the drip chamber includes determining if the plurality of summation values includes a plurality of contiguous summation values within a predetermined range greater than a minimum value and less than a maximum value.

30. The method according to claim 25, further comprising the act of converting each pixel of the difference image to a squared value of each pixel after the subtracting act and prior to the converting act.

31. The method according to claim 1, further comprising the acts of:

creating a first thresholded image from the image by comparing each pixel of the image to a threshold value;

determining a set of pixels within the first thresholded image connected to a predetermined set of pixels within the first thresholded image;

filtering all remaining pixels of the first thresholded image that are not within the set of pixels, the filter operates on a pixel-by-pixel basis within the time domain to generate a first filtered image;

removing pixels determined to not be part of a drop from the first thresholded image using the first filtered image to generate a second image;

determining a second set of pixels within the second image connected to a predetermined set of pixels within the second image to generate a third image, the third image identifies the second set of pixels within the second image;

determining a first length of the drop by counting the number of rows containing pixels corresponding to the second set of pixels within the third image, the first length corresponding to a first estimated drop size;

updating the dynamic background image using the image;

creating a second thresholded image by comparing the image with the dynamic background image;

summing the rows of the second thresholded image to create a plurality of row sums, each row sum corresponds to a row of the second thresholded image;

starting at a row position of the second thresholded image having a first sum of the plurality of sums that corresponds to the first length;

incrementing the row position until the row position corresponds to a corresponding row sum that is zero;

determining a second length is equal to the present row position, the second length corresponding to a second estimated drop size; and

averaging the first and second lengths to determine an average length, the average length corresponding to a third estimated drop size.

32. The method according to claim 1, further comprising the act of updating each pixel of the dynamic background image using a low-pass filter.

33. The method according to claim 1, further comprising the act of remotely controlling the flow rate by a monitoring client.

34. The method according to claim 33, wherein the monitoring client is a tablet.

35. A flow meter, comprising:

a coupler adapted to couple to a drip chamber;

a support member operatively coupled to the coupler;

an image sensor having a field of view and operatively coupled to the support member, wherein the image sensor is positioned to view the drip chamber within the field of view; and

at least one processor operatively coupled to the image sensor to receive image data therefrom, wherein the at least one processor is configured to;

capture an image of a drip chamber using an image sensor;

compare the image of a drip chamber with a dynamic background image wherein the dynamic background image contains a pattern having a plurality of lines; and

adjust a flow rate of fluid flowing through the fluid line in accordance with the comparison between the image of the drip chamber and the dynamic background image.

36. The flow meter according to claim 35, wherein the dynamic background image is generated using another image captured by the image sensor.

37. The flow meter according to claim 35, wherein the at least one processor is further configured to estimate a volume of the drop using the comparison between the image of the drip chamber and the dynamic background image.

38. The flow meter according to claim 35, wherein the at least one processor is further configured to identify a plurality of pixels of interest within the image.

39. The flow meter according to claim 38, wherein the plurality of pixels of interest are identified by comparing the image to the dynamic background image.

40. The flow meter according to claim 38, wherein the at least one processor is further configured to determine a subset of pixels within the plurality of pixels of interest, wherein each pixel of the plurality of pixels is determined to be within the subset of pixels when there is a path to a baseline corresponding to the drip chamber.

41. The flow meter according to claim 38, wherein the at least one processor is further configured to determine a volume of the drop based upon the plurality of pixels of interest.

42. The flow meter according to claim 35, wherein the at least one processor is further configured to initialize the dynamic background image.

43. The flow meter according to claim 35, wherein the at least one processor is further configured to update the dynamic background image using the image captured by the image sensor.

44. The flow meter according to claim 43, wherein the dynamic background image is updated in accordance with:

P_{background,i,j}=P_{background,i,j}(1−

α

_background)+α

_backgroundP_input,i,j.

45. The flow meter according to claim 35, wherein the at least one processor is further configured to update an array of variances using the image captured by the image sensor.

46. The flow meter according to claim 45, wherein the array of variances is updated in accordance with:

σ

_temp²=(P_{background,i,j}−

P_input,i,j)²

σ

_{background,i,j}²=σ

_{background,i,j}²(1−

β

_background)+β

_backgroundσ

_temp².

47. The flow meter according to claim 35, wherein the at least one processor is further configured to update an array of integers in accordance with the image captured by the image sensor.

48. The flow meter according to claim 47, wherein each integer of the array of integers corresponds to a number of updates of a pixel of the dynamic background image.

49. The flow meter according to claim 48, wherein the comparison of the image to the dynamic background image only compares pixels within the image to pixels within the dynamic background image if a respective integer of the array of integers indicates a respective pixel within the dynamic background image has been updated at least a predetermined number of times.

50. The flow meter according to claim 35, wherein the at least one processor is further configured to:

identify a drop in the image and a predetermined band near an edge of the drop; and

initialize the dynamic background image by setting each pixel of the dynamic background image to the image unless it is within the identified drop or the predetermined band near the edge of the drop.

51. The flow meter according to claim 50, wherein the at least one processor is further configured to set a pixel of the dynamic background image to a predetermined value if a corresponding pixel of the image is within the identified drop or the predetermined band near the edge of the drop.

52. The flow meter according to claim 51, wherein the corresponding pixel of the image has a location corresponding to a location of the pixel of the dynamic background image.

53. The flow meter according to claim 35, wherein the at least one processor is further configured to determine the baseline corresponding to an opening of the drip chamber.

54. The flow meter according to claim 35, wherein the determination of a subset of pixels within the plurality of pixels of interest that corresponds to a drop includes determining each of the plurality of pixels of interest is within the subset of pixels if the respective pixel of the plurality of pixels has a contiguous path back to the baseline of the drop forming at an opening of the drip chamber.

55. The flow meter according to claim 35, wherein the at least one processor is further configured to:

identify the drop within the image and a predetermined band near an edge of the drop;

initialize the dynamic background image by setting each pixel to the image unless it is within the identified drop or the predetermined band near the edge of the drop;

set pixels within the region of the drop or within the predetermined band to a predetermined value;

initialize an array of integers; and

initialize an array of variances.

56. The flow meter according to claim 55, wherein the at least one processor is further configured to update the dynamic background image, the array of integers, and the array of variances using the image.

57. The flow meter according to claim 35, wherein the dynamic background image is configured to filter out low frequency artifacts.

58. The flow meter according to claim 35, wherein the at least one processor is further configured to:

subtract the image from the dynamic background image to thereby generate a difference image;

convert each pixel of the difference image to a true value if an absolute value of a respective pixel is beyond a predetermined threshold or to a false value if the absolute value of the respective pixel is less than the predetermined threshold;

sum each row of the converted difference image to generate a plurality of summation values, wherein each summation value of the plurality of summation values corresponds to a respective row of the converted difference image; and

examine the plurality of summation values.

59. The flow meter according to claim 58, wherein the at least one processor is further configured to examine the plurality of summation values by determining if a free flow condition exists within the drip chamber.

60. The flow meter according to claim 58, wherein the at least one processor is further configured to examine the plurality of summation values by determining if the free flow condition by determining if the plurality of summation values includes a plurality of contiguous summation values above another predetermined threshold.

61. The flow meter according to claim 58, wherein the examination of the plurality of summation values includes determining if a drop has been formed within the drip chamber.

62. The flow meter according to claim 61, wherein the determination of whether the drop has been formed within the drip chamber includes determining if the plurality of summation values includes a plurality of contiguous summation values within a predetermined range greater than a minimum value and less than a maximum value.

63. The flow meter according to claim 58, wherein the at least one processor is further configured to convert each pixel of the difference image to a squared value of each pixel after the subtraction and prior to the conversion.

64. The flow meter according to claim 35, wherein the at least one processor is further configured to:

create a first thresholded image from the image by comparing each pixel of the image to a threshold value;

determine a set of pixels within the first thresholded image connected to a predetermined set of pixels within the first thresholded image;

filter all remaining pixels of the first thresholded image that are not within the set of pixels, the filter operates on a pixel-by-pixel basis within the time domain to generate a first filtered image;

remove pixels determined to not be part of a drop from the first thresholded image using the first filtered image to generate a second image;

determine a second set of pixels within the second image connected to a predetermined set of pixels within the second image to generate a third image, the third image identifies the second set of pixels within the second image;

determine a first length of the drop by counting the number of rows containing pixels corresponding to the second set of pixels within the third image, the first length corresponding to a first estimated drop size;

update the dynamic background image using the image;

create a second thresholded image by comparing the image with the dynamic background image;

sum the rows of the second thresholded image to create a plurality of row sums, each row sum corresponds to a row of the second thresholded image;

start at a row position of the second thresholded image having a first sum of the plurality of sums that corresponds to the first length;

increment the row position until the row position corresponds to a corresponding row sum that is zero;

determine a second length is equal to the present row position, the second length corresponding to a second estimated drop size; and

average the first and second lengths to determine an average length, the average length corresponding to a third estimated drop size.

65. The flow meter according to claim 35, wherein the at least one processor is further configured to update each pixel of the dynamic background image using a low-pass filter.

66. The flow meter according to claim 35, wherein the at least one processor is further configured to bed remotely controlled by a monitoring client.

67. The flow meter according to claim 66, wherein the monitoring client is a tablet.