Method for estimating blood component quantities in surgical textiles

1. A system for measuring blood content, the system comprising:

a color imaging system configured to acquire one or more color images of a surgical textile;

an infrared imaging system configured to acquire one or more infrared images of the surgical textile; and

a processor configured to:

generate a depth image of depth information from at least one of the one or more infrared images;

identify a shape of the surgical textile using the depth image;

generate shape information of the identified shape of the surgical textile from the depth image;

use the shape information to identify surgical textile pixels that correspond to the surgical textile in the one or more color images; and

extract blood information from the surgical textile pixels.

2. The system of claim 1 , wherein the processor is further configured to transform the infrared images to a coordinate system corresponding to the one or more color images.

3. The system of claim 1 , wherein the processor is further configured to identify a set of pixels that represent a planar surface in the depth image.

4. The system of claim 1 , wherein the processor is further configured to detect a surgical textile image perimeter in the depth image.

5. The system of claim 4 , wherein detection of the surgical textile image perimeter is performed by looking for a sharp vertical depth drop-off in the depth image.

6. The system of claim 1 , wherein the processor is further configured to downsample at least one of the depth image or at least one of the one or more infrared images.

7. The system of claim 6 , wherein the processor is further configured to generate a mask image from the downsampled depth image.

8. The system of claim 7 , wherein the processor is further configured to upsample the mask image.

9. The system of claim 1 , wherein the processor is further configured to perform fill-in of missing infrared pixel region in the one or more infrared images.

10. The system of claim 4 , wherein the processor is further configured to generate a mask image using the detected perimeter.

11. The system of claim 10 , wherein the processor is further configured to transform the mask image to a coordinate system of the one or more color images.

12. The system of claim 10 , wherein the detected perimeter is a top edge and a bottom edge of a surgical textile image.

13. The system of claim 10 , wherein the detected perimeter comprises opposing edges of a surgical textile image.

14. The system of claim 10 , wherein the detected perimeter comprises corners of a surgical textile image.

15. A method of analyzing an object containing a blood component, the method comprising:

for the object containing the blood component, acquiring both a depth image and a color image both of the object containing the blood component;

using the depth image to detect the object in a field of view; and

using the color image to estimate a blood component characteristic of the blood component contained in the object.

16. The method of claim 15 , further comprising:

generating an image mask using the depth image; and

applying the image mask to the color image to eliminate background pixels.

17. The method of claim 16 , further comprising:

applying at least one of erosion image processing or dilation image processing to the depth image.

18. A method of performing fluid monitoring, comprising:

capturing an infrared image of a surgical textile in a field of view;

capturing a color image of the surgical textile in the field of view;

generating an image mask using the infrared image of the surgical textile; and

using the image mask with the color image to identify a region of the color image corresponding to the surgical textile.

19. The method of claim 18 , further comprising transforming the infrared image to a geometry perspective of the color image.

20. The method of claim 18 , further comprising downsampling the infrared image prior to generating the image mask.

21. The method of claim 20 , further comprising upsampling the image mask before using the image mask to identify the region of the color image.