IV monitoring by video and image processing

• US 8,531,517 B2
• Filed: 07/15/2010
• Issued: 09/10/2013
• Est. Priority Date: 07/15/2010
• Status: Expired due to Fees

• Current Assignee: Kai Tao
• Original Assignee: Kai Tao
• Inventors: Tao, Kai
• Primary Examiner(s): Perungavoor, Sath V
• Assistant Examiner(s): Anderson, Matthew J
• Application Number:
  US12/804,163
• Publication Number:
  US 20120013735A1
• Time in Patent Office: 1,153 Days
• Field of Search: 604/253, 604/251
• US Class Current: 348/135
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

We describe a method and apparatus for monitoring the dripping speed in IV process, as well as detecting the its end. The apparatus includes a camera and a processing unit to analyze the information from the acquired video. Features from the image sequence are extracted and the dripping speed is computed accordingly by discrete Fourier transform. The apparatus is also capable of detecting the end of the dripping process by finding the location of liquid surface in the drip chamber. We also describe the use of barcode to provide information to the monitoring device and program.

Claims

1. An apparatus for IV dripping speed monitoring, comprising:

a containing box that holds the drip chamber;

an image capturing device, to capture video of the dripping process;

a processing unit to perform analysis of the captured video;

wherein said processing unit monitors the dripping speed based on a signal which is obtained from analyzing the image sequence, wherein the elements of the signal are influenced or driven by the dripping process; and

wherein the dripping speed is determined by performing Fourier analysis methods on the signal.

2. The apparatus of claim 1, wherein the Fourier analysis methods include a discrete Fourier transform.

3. The apparatus of claim 1, wherein the containing box has light sources arranged inside;

and part or all of the containing box is made of non-transparent material.

4. A method for obtaining a characteristic value of a drip from images of an IV dripping chamber, comprising:

determining connected components indicative of drips within the image using a connectivity criteria;

ranking the connected components according to a numerical measure of their respective size;

identifying a connected component of a certain rank from the ranked connected components; and

computing a characteristic value, indicative of the vertical location of the drips during the dripping process, for the identified connected component.

5. The method of claim 4, wherein the identified component is the one of the largest size or largest connected component.

6. The method of claim 4, wherein the characteristic value is the identified component'"'"'s average pixel vertical location.

7. The method of claim 4, further comprising:

processing the images with techniques including image enhancement, thresholding, or reducing or removing relatively smaller parts in the image, or combinations thereof before applying connectivity criteria.

8. The method of claim 7, further comprising:

combining said techniques in an order beginning with image enhancement and ending with removal or reduction of the smaller parts of the image.

9. The method of claim 7, wherein the image enhancement techniques include the use of a Sobel operator, a Prewitt operator, or a Laplacian operator, or combinations thereof.

10. The method of claim 7, wherein the thresholding techniques include the use of Otsu thresholding, automatic thresholding, or thresholding using a predetermined value.

11. The method of claim 7, wherein the reduction or removal of relatively smaller parts in the image include the use of erosion or removing parts for which the numerical measure of its size is below a threshold.

12. A method for obtaining a characteristic value of a drip from images of an IV dripping chamber, comprising:

processing the image with techniques including image enhancement, thresholding, or reducing or removing relatively smaller parts in the image, or combinations thereof;

determining connected components indicative of drips within the processed image using a connectivity criteria;

ranking the connected components according to a numerical measure of their respective size;

identifying a connected component of a certain rank from the ranked connected components, wherein the identified component is the one of the largest size or largest connected component;

computing a characteristic value, indicative of the vertical location of the drips during the dripping process, for the identified connected component; and

wherein the image enhancement techniques include the use of a Sobel operator, a Prewitt operator, or a Laplacian operator, or combinations thereof.

13. The method of claim 12, wherein the thresholding techniques include the use of Otsu thresholding, automatic thresholding, or thresholding using a predetermined value.

14. The method of claim 12, wherein the reduction or removal of relatively smaller parts in the image include the use of erosion or removing parts for which the numerical measure of its size is below a threshold.

15. A method for determining IV dripping speed with Fourier analysis methods, comprising:

capturing a sequence of images of an IV dripping sequence, using an image capturing device, wherein at least some of the images contain part or all of the dripping chamber;

processing at least some temporally evenly spaced images and extracting from each image a numerical value that is influenced or driven by the dripping process and storing the values into a vector;

using a Fourier analysis method to determine periodicity in the stored vector; and

using the periodicity combined with the temporal spacing of the images to calculate the dripping speed.

16. The method of claim 15, wherein the Fourier analysis method further comprises,

performing a discrete Fourier transform on the stored vector;

indexing the total spectrum component;

finding the fourier component of the largest magnitude, excluding at index zero which corresponds to the DC component in the vector, in either the entire left or right of the spectrum, or an interval of the left or right half of the spectrum whose length is smaller than the full length of the selected half, provided that the interval is wide enough to cover the Fourier component whose index is indicative of the vector'"'"'s periodicity;

storing said index;

using the index as the number of periods; and

calculating the dripping speed by utilizing the periodicity information and the temporal distance of the images from which the vector elements were computed.

17. A method for determining IV dripping speed comprising:

capturing a sequence of images of an IV dripping sequence, using an image capturing device, wherein at least some of the images contain part or all of the dripping chamber;

processing some temporally evenly spaced images and extracting from each image a numerical value that is influenced or driven by the dripping process and storing the values into a vector, wherein the extraction is of the drip trajectory less than 4 cm from the lowest part of the dripping mouth from which the drip comes out;

applying frequency estimation methods to determine periodicity in the stored vector; and

calculating the dripping speed by utilizing the periodicity information and the temporal distance of the images from which the vector elements were computed.