Remote contactless liquid container volumetry
In an embodiment, a volumetry method is provided. The method can include receiving one or more 2D images of a site including one or more containers configured to hold a liquid, the 2D images being acquired at a first time. The method can also include identifying a container within the 2D images. The method can further include selecting an identified container within the 2D images for volumetric analysis based upon a degree of occlusion of its front facing surface. The method can additionally include classifying a portion of the selected container containing the liquid. The method can further include determining the volume of liquid held within the container based upon the classified portion.
1. A method, comprising:
acquiring, by one or more cameras, one or more 2D images of a site including one or more containers configured to hold a liquid, the 2D images being acquired at a first time;
identifying, by one or more processors, a container within the one or more of the 2D images;
determining, by the one or more processors, a front facing surface of the identified container;
determining, by the one or more processors, an occluded portion of the front facing surface of the identified container;
determining, by the one or more processors, that the occluded portion is less than a predetermined amount of the front facing surface;
selecting, by the one or more processors, the identified container within the one or more 2D images for volumetric analysis based upon the determining that the occluded portion is less than the predetermined amount;
classifying, by the one or more processors, a portion of the selected container containing the liquid; and
determining, by the one or more processors, the volume of liquid held within the container based upon the classified portion.
2. The method of claim 1 , further comprising, by the one or more processors:
determining a ratio of a height of the liquid held within the selected container to a total height of the selected container; and
determining a volume of the liquid held within the selected container based upon the determined ratio and a total volume of the selected container.
3. The method of claim 1 , further comprising receiving, by the one or more processors, a 3D model representing the site at a second time prior to the first time.
4. The method of claim 1 , wherein the one or more 2D images are at least one of infrared (IR) images, color images, gray-scale images, or a combination thereof.
5. The method of claim 3 , further comprising, by the one or more processors:
determining a boundary of the identified container within the one or more 2D images based upon the 3D model.
6. The method of claim 5 , further comprising generating, by the one or more processors, a processed image by at least one of deskewing or dewarping the isolated front-facing surface of the selected container prior to classifying the portion of the selected container holding the liquid.
7. The method of claim 6 , further comprising selecting, by the one or more processors, a center portion of the processed image prior to classifying the portion of the selected container holding the liquid.
8. The method of claim 5 , further comprising generating, by the one or more processors, a processed image by binarizing the isolated front-facing surface of the selected container prior to classifying the portion of the selected container holding the liquid.
9. The method of claim 1 , wherein the container is a cylinder.
10. The method of claim 2 , wherein the ratio of the height of the liquid held within the container to the total height of the selected container is determined as a function of horizontal position, further wherein the height is determined at multiple horizontal locations of the container using a linear regression.
11. A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving, from one or more cameras, one or more 2D images of a site including one or more containers configured to hold a liquid, the 2D images being acquired at a first time;
identifying a container within the one or more of the 2D images;
determining a front facing surface of the identified container;
determining an occluded portion of the front facing surface of the identified container;
determining that the occluded portion is less than a predetermined amount of the front facing surface;
selecting the identified container within the one or more 2D images for volumetric analysis based upon the determining that the occluded portion is less than the predetermined amount;
classifying a portion of the selected container containing the liquid; and
determining the volume of liquid held within the container based upon the classified portion.
12. The computer program product of claim 11 , further configured to perform operations comprising:
determining a ratio of a height of the liquid held within the selected container to a total height of the selected container; and
determining a volume of the liquid held within the selected container based upon the determined ratio and a total volume of the selected container.
13. The computer program product of claim 11 , further configured to perform operations comprising receiving a 3D model representing the site at a second time prior to the first time.
14. The computer program product of claim 11 , wherein the one or more 2D images are at least one of infrared (IR) images, color images, gray-scale images, or a combination thereof.
15. The computer program product of claim 13 , further configured to perform operations comprising:
determining a boundary of the identified container within the one or more 2D images based upon the 3D model.
16. The computer program product of claim 15 , further configured to perform operations comprising generating a processed image by at least one of deskewing or dewarping the isolated front-facing surface of the selected container prior to classifying the portion of the selected container holding the liquid.
17. The computer program product of claim 16 , further configured to perform operations comprising selecting a center portion of the processed image prior to classifying the portion of the selected container holding the liquid.
18. The computer program product of claim 15 , further configured to perform operations comprising generating a processed image by binarizing the isolated front-facing surface of the selected container prior to classifying the portion of the selected container holding the liquid.
19. The computer program product of claim 11 , wherein the container is a cylinder.
20. The computer program product of claim 12 , wherein the ratio of the height of the liquid held within the container to the total height of the selected container is determined as a function of horizontal position, further wherein the height is determined at multiple horizontal locations of the container using a linear regression.