Methods for unit load device (ULD) door tarp detection
Methods for determining a unit load device (ULD) door status are disclosed herein. An example method includes capturing a set of image data featuring the ULD. The example method further includes segmenting the set of image data to identify a top portion of the ULD, and determining an amplitude of the top portion of the ULD. The example method further includes determining the ULD door status based on whether the amplitude of the top portion of the ULD exceeds an amplitude threshold.
1. A method for determining a unit load device (ULD) door status, comprising:
capturing a set of image data featuring the ULD;
segmenting the set of image data to identify a top portion of the ULD;
determining an amplitude of the top portion of the ULD; and
determining the ULD door status based on whether the amplitude of the top portion of the ULD exceeds an amplitude threshold,
wherein the set of image data is a first set of image data, and the method further comprises:
(a) capturing a second set of image data featuring the ULD a duration D after capturing the first set of image data;
(b) designating the second set of image data as a current set of image data;
(c) segmenting the current set of image data to identify a current top portion of the ULD;
(d) determining a current amplitude of the current top portion of the ULD;
(e) determining a current ULD door status based on whether the current amplitude of the current top portion of the ULD exceeds the amplitude threshold;
(f) designating the current set of image data as a prior set of image data;
(g) capturing a subsequent set of image data featuring the ULD the duration D after capturing the prior set of image data;
(h) designating the subsequent set of image data as the current set of image data; and
(i) iteratively performing steps (c)-(i) until the current amplitude does not exceed the amplitude threshold.
2. The method of claim 1 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) an amplitude image that is depth-aligned with the three-dimensional depth image.
3. The method of claim 1 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) a red-green-blue (RGB) image, and wherein the method further comprises:
aligning the RGB image with the three-dimensional depth image.
4. The method of claim 1 , wherein the set of image data includes a plurality of pixels, and the method further comprising:
identifying the top portion of the ULD based on a predetermined height value and a predetermined height threshold; and
comparing a depth value of each pixel in the plurality of pixels to a predetermined depth value corresponding to the top portion of the ULD.
5. The method of claim 1 , wherein the ULD door status is open when the amplitude of the top portion of the ULD exceeds the amplitude threshold, and wherein the ULD door status is closed when the amplitude of the top portion of the ULD does not exceed the amplitude threshold.
6. The method of claim 1 , further comprising:
training a machine learning model using (i) a plurality of sets of image data featuring a respective ULD, (ii) a plurality of segmented images, each segmented image featuring a top portion of a respective ULD, and (iii) one or more amplitude values from each of the plurality of segmented images, wherein each amplitude value represents an amplitude of the top portion of the respective ULD; and
applying the machine learning model to the set of image data featuring the ULD to determine the ULD door status.
7. A system for determining a unit load device (ULD) door status, comprising:
a housing;
an imaging assembly at least partially within the housing and configured to capture a set of image data featuring the ULD;
one or more processors; and
a non-transitory computer-readable memory coupled to the imaging assembly and the one or more processors, the memory storing instructions thereon that, when executed by the one or more processors, cause the one or more processors to:
segment the set of image data to identify a top portion of the ULD,
determine an amplitude of the top portion of the ULD, and
determine the ULD door status based on whether the amplitude of the top portion of the ULD exceeds an amplitude threshold,
wherein the set of image data is a first set of image data, and the instructions, when executed by the one or more processors, further cause the one or more processors to:
(a) capture a second set of image data featuring the ULD a duration D after capturing the first set of image data;
(b) designate the second set of image data as a current set of image data;
(c) segment the current set of image data to identify a current top portion of the ULD;
(d) determine a current amplitude of the current top portion of the ULD;
(e) determine a current ULD door status based on whether the current amplitude of the current top portion of the ULD exceeds the amplitude threshold;
(f) designate the current set of image data as a prior set of image data;
(g) capture a subsequent set of image data featuring the ULD the duration D after capturing the prior set of image data;
(h) designate the subsequent set of image data as the current set of image data; and
(i) iteratively perform steps (c)-(i) until the current amplitude does not exceed the amplitude threshold.
8. The system of claim 7 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) an amplitude image that is depth-aligned with the three-dimensional depth image.
9. The system of claim 7 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) a red-green-blue (RGB) image, and wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
align the RGB image with the three-dimensional depth image.
10. The system of claim 7 , wherein the set of image data includes a plurality of pixels, and the instructions, when executed by the one or more processors, further cause the one or more processors to:
identify the top portion of the ULD based on a predetermined height value and a predetermined height threshold; and
compare a depth value of each pixel in the plurality of pixels to a predetermined depth value corresponding to the top portion of the ULD.
11. The system of claim 7 , wherein the ULD door status is open when the amplitude of the top portion of the ULD exceeds the amplitude threshold, and wherein the ULD door status is closed when the amplitude of the top portion of the ULD does not exceed the amplitude threshold.
12. The system of claim 7 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
train a machine learning model using (i) a plurality of sets of image data featuring a respective ULD, (ii) a plurality of segmented images, each segmented image featuring a top portion of a respective ULD, and (iii) one or more amplitude values from each of the plurality of segmented images, wherein each amplitude value represents an amplitude of the top portion of the respective ULD; and
apply the machine learning model to the set of image data featuring the ULD to determine the ULD door status.
13. A tangible machine-readable medium comprising instructions for determining a unit load device (ULD) door status that, when executed, cause a machine to at least:
capture a set of image data featuring the ULD;
segment the set of image data to identify a top portion of the ULD;
determine an amplitude of the top portion of the ULD; and
determine the ULD door status based on whether the amplitude of the top portion of the ULD exceeds an amplitude threshold,
wherein the set of image data is a first set of image data, and the instructions, when executed, further cause the machine to:
(a) capture a second set of image data featuring the ULD a duration D after capturing the first set of image data;
(b) designate the second set of image data as a current set of image data;
(c) segment the current set of image data to identify a current top portion of the ULD;
(d) determine a current amplitude of the current top portion of the ULD;
(e) determine a current ULD door status based on whether the current amplitude of the current top portion of the ULD exceeds the amplitude threshold;
(f) designate the current set of image data as a prior set of image data;
(g) capture a subsequent set of image data featuring the ULD the duration D after capturing the prior set of image data;
(h) designate the subsequent set of image data as the current set of image data; and
(i) iteratively perform steps (c)-(i) until the current amplitude does not exceed the amplitude threshold.
14. The tangible machine-readable medium of claim 13 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) an amplitude image that is depth-aligned with the three-dimensional depth image.
15. The tangible machine-readable medium of claim 13 , wherein the set of image data featuring the ULD comprises (i) a three-dimensional depth image and (ii) a red-green-blue (RGB) image, and wherein the instructions, when executed, further cause the machine to:
align the RGB image with the three-dimensional depth image.
16. The tangible machine-readable medium of claim 13 , wherein the set of image data includes a plurality of pixels, and the instructions, when executed, further cause the machine to:
identify the top portion of the ULD based on a predetermined height value and a predetermined height threshold; and
compare a depth value of each pixel in the plurality of pixels to a predetermined depth value corresponding to the top portion of the ULD.
17. The tangible machine-readable medium of claim 13 , wherein the ULD door status is open when the amplitude of the top portion of the ULD exceeds the amplitude threshold, and wherein the ULD door status is closed when the amplitude of the top portion of the ULD does not exceed the amplitude threshold.