Methods and systems for performing object dimensioning
Aspects of the present disclosure include obtaining images from a time-of-flight (TOF) sensor for determining dimensions of an object including obtaining, from the TOF sensor, multiple images including the object, validating whether the multiple images are taken at desired poses relative to the object, and where the multiple images are validated as taken at the desired poses, providing the multiple images for object dimensioning to compute or display dimensions of the object.
1 . A computer-implemented method for obtaining images from a time-of-flight (TOF) sensor for determining dimensions of an object, comprising:
obtaining, from the TOF sensor, multiple images including the object, wherein each image of the multiple images is captured at a different position around the object;
determining, for each of the multiple images, a position of capture relative to the object;
validating, based on the determined position of capture for each of the multiple images, whether the multiple images are taken at desired poses relative to the object; and
where the multiple images are validated as taken at the desired poses, providing the multiple images for object dimensioning to compute dimensions of the object; and
outputting the dimensions of the object for display.
2 . The computer-implemented method of claim 1 , further comprising receiving, from a positioning sensor associated with the TOF sensor, the position of capture for each of the multiple images, wherein validating whether the multiple images are taken at desired poses is based on comparing at least a first position of capture for one of the multiple images and at least a second position of capture for a different one of the multiple images.
3 . The computer-implemented method of claim 1 , wherein validating whether the multiple images are taken at desired poses includes determining, based on the determined position of capture for each of the multiple images, that the multiple images are taken at positions separated by substantially 30 degrees in azimuth around the object.
4 . The computer-implemented method of claim 3 , wherein validating whether the multiple images are taken at desired poses includes determining that the multiple images include at least four images that are taken at positions separated by substantially 30 degrees in azimuth around the object.
5 . The computer-implemented method of claim 1 , wherein validating whether the multiple images are taken at desired poses includes validating that the multiple images include, for each position of capture, at least two images.
6 . The computer-implemented method of claim 5 , wherein validating whether the multiple images are taken at desired poses includes validating that the at least two images result in a threshold signal-to-noise ratio.
7 . The computer-implemented method of claim 1 , wherein validating whether the multiple images are taken at the desired poses is based on a model of the object, wherein the desired poses are inferred from the model of the object.
8 . A system comprising:
a memory; and
a processor coupled to the memory, wherein the processor is configured to:
obtain, from a time-of-flight (TOF) sensor, multiple images including an object, wherein each image of the multiple images is captured at a different position around the object;
determine, for each of the multiple images, a position of capture relative to the object;
validate, based on the determined position of capture for each of the multiple images, whether the multiple images are taken at desired poses relative to the object; and
where the multiple images are validated as taken at the desired poses, provide the multiple images for object dimensioning to compute or display dimensions of the object.
9 . The system of claim 8 , wherein the processor is further configured to receive, from a positioning sensor associated with the TOF sensor, the position of capture for each of the multiple images, wherein the processor is configured to validate whether the multiple images are taken at desired poses based on comparing at least a first position of capture for one of the multiple images and at least a second position of capture for a different one of the multiple images.
10 . The system of claim 8 , wherein the processor is configured to validate whether the multiple images are taken at desired poses including determining, based on the determined position of capture for each of the multiple images, that the multiple images are taken at positions separated by substantially 30 degrees in azimuth around the object.
11 . The system of claim 10 , wherein the processor is configured to validate whether the multiple images are taken at desired poses including determining that the multiple images include at least four images that are taken at positions separated by substantially 30 degrees in azimuth around the object.
12 . The system of claim 8 , wherein the processor is configured to validate whether the multiple images are taken at desired poses including validating that the multiple images include, for each position of capture, at least two images.
13 . The system of claim 12 , wherein the processor is configured to validate whether the multiple images are taken at desired poses including validating that the at least two images result in a threshold signal-to-noise ratio.
14 . The system of claim 8 , wherein the processor is configured to validate whether the multiple images are taken at the desired poses based on a model of the object, wherein the desired poses are inferred from the model of the object.
15 . A non-transitory computer-readable medium, comprising code executable by one or more processors for obtaining images from a time-of-flight (TOF) sensor for determining dimensions of an object, the code comprising code for:
obtaining, from the TOF sensor, multiple images including the object, wherein each image of the multiple images is captured at a different position around the object;
determining, for each of the multiple images, a position of capture relative to the object;
validating, based on the determined position of capture for each of the multiple images, whether the multiple images are taken at desired poses relative to the object; and
where the multiple images are validated as taken at the desired poses, providing the multiple images for object dimensioning to compute or display dimensions of the object.
16 . The non-transitory computer-readable medium of claim 15 , further comprising code for receiving, from a positioning sensor associated with the TOF sensor, the position of capture for each of the multiple images, wherein the code for validating validates whether the multiple images are taken at desired poses based on comparing at least a first position of capture for one of the multiple images and at least a second position of capture for a different one of the multiple images.
17 . The non-transitory computer-readable medium of claim 15 , wherein the code for validating validates whether the multiple images are taken at desired poses including determining, based on the determined position of capture for each of the multiple images, that the multiple images are taken at positions separated by substantially 30 degrees in azimuth around the object.
18 . The non-transitory computer-readable medium of claim 17 , wherein the code for validating validates whether the multiple images are taken at desired poses including determining that the multiple images include at least four images that are taken at positions separated by substantially 30 degrees in azimuth around the object.
19 . The non-transitory computer-readable medium of claim 15 , wherein the code for validating validates whether the multiple images are taken at desired poses including validating that the multiple images include, for each position of capture, at least two images.
20 . The non-transitory computer-readable medium of claim 15 , wherein the code for validating validates whether the multiple images are taken at the desired poses based on a model of the object, wherein the desired poses are inferred from the model of the object.