Systems and methods for mobile parcel dimension calculation and predictive condition analysis

Patent metadata

Field	Value
Publication number	US-10885653-B2
Application number	US-201916245916-A
Country	US
Kind code	B2
Filing date	Jan 11, 2019
Priority date	Jan 12, 2018
Publication date	Jan 5, 2021
Grant date	Jan 5, 2021

Abstract

Present aspects are directed to a system that receives digital images of parcels at various points throughout a transportation and logistics network. Based on analysis of a single digital image of a parcel, the dimensions of the parcel are detected and calculated. A single digital image of a parcel is captured at various points throughout a transit or shipping network. The single digital image is processed using computer vision for image manipulation. Key identifying points of the parcel (e.g., a label or bar code) can be detected through the processing. The processed digital image is input into a mathematical model that generates an estimate for all dimensions of the parcel.

First claim

The invention claimed is:

1. An apparatus for programmatic parcel dimension determination in a parcel transit network, the parcel transit network comprising an origin interaction point, a plurality of parcel interaction points, and a destination interaction point, the apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:
receive a first parcel digital image from a mobile computing device at the origin interaction point, the first parcel digital image associated with and representative of a parcel being transported from the origin interaction point to the destination interaction point via the plurality of parcel interaction points;
identify, using digital detection, a first group of pixels in the first parcel digital image corresponding to a first upper rear corner of the parcel, and a second group of pixels in the first parcel digital image corresponding to a second upper rear corner of the parcel,
wherein the first upper rear corner and the second upper rear corner are separated by an upper rear edge of the parcel, the upper rear edge of the parcel having a length H 1 ;
identify, using digital detection, a third group of pixels in the first parcel digital image corresponding to a first upper front corner, and a fourth group of pixels in the first parcel digital image corresponding to a first lower front corner of the parcel in the first parcel digital image,
wherein the first upper front corner and the first lower front corner are separated by a first front side edge of the parcel, the first front side edge of the parcel having a length DL, and
wherein the first upper front corner and the first upper rear corner are separated by a first upper side edge of the parcel, the first upper side edge of the parcel having a length UL;
identify, using digital detection, a fifth group of pixels in the first parcel digital image corresponding to a second lower front corner and a sixth group of pixels in the first parcel digital image corresponding to a second lower rear corner of the parcel in the first parcel digital image,
wherein the second lower front corner and the second lower rear corner are separated by a second lower side edge of the parcel, the second lower side edge of the parcel having a length DR,
wherein the second lower front corner and the first lower front corner are separated by a lower front edge of the parcel, the lower front edge of the parcel having a length H 2 , and
wherein the second upper rear corner and the second lower rear corner are separated by a second rear side edge of the parcel, the second rear side edge of the parcel having a length UR;
identify, using digital detection, a seventh group of pixels in the first parcel digital image corresponding to a reference label affixed to the parcel, the reference label having a known first edge length R 1 and a known second edge length R 2 ;
programmatically calculate, using the identified groups of pixels, each of lengths H 1 , UL, DL, DR, H 2 , and U 2 , as well as an associated angle for each length relative a the horizontal axis of the first parcel digital image;
programmatically determine correction factors to apply to each of lengths H 1 , UL, DL, DR, H 2 , and U 2 based upon a scale programmatically calculated based upon R 1 and R 2 ;
apply the correction factors to each of lengths H 1 , UL, DL, DR, H 2 , and U 2 ;
confirm that length H 1 length H 2 , length DR length UL, and length UR length DL; and
upon confirming that length H 1 length H 2 , length DR length UL, and length UR length DL, scale the corrected lengths to inches and output the scaled corrected lengths as calculated dimensions of the parcel.

2. The apparatus of claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to programmatically determine the correction factors and the scale by:
programmatically determining an angular skew between a first relative angle between lengths R 1 and H 1 and a second relative angle between lengths R 1 and H 2 ;
upon determining that the angular skew is below an angular skew threshold,
programmatically calculating a vertical angle of the parcel in the first parcel digital image according to the equation

sin

-
1

⁡

(

R
⁢

⁢
1

R
⁢

⁢
2

)

;

programmatically calculating a front side angle of the parcel in the first parcel digital image according to the equation and

90
⁢
°

-

sin

-
1

⁡

(

R
⁢

⁢
1

R
⁢

⁢
2

)

;

using the vertical angle of the parcel and the front side angle of the parcel, calculating correction factors facilitating generation, from lengths R 1 and R 2 , of scales for each of the upper rear edge, first upper side edge, first front side edge, lower front edge, second lower side edge, and second rear side edge of the parcel.

3. The apparatus of claim 2 , wherein, upon determining that the angular skew exceeds the angular skew threshold, apply corrective trigonometric calculations before calculating the vertical angle of the parcel.

4. The apparatus of claim 3 , wherein applying the corrective trigonometric calculations comprises adjusting a length of an axis based on the angular skew.

5. The apparatus of claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to:
compare the calculated dimensions of the parcel to known dimension information about the parcel retrieved based upon parcel information obtained from the reference label; and
upon determining that a difference between the calculated dimensions and the known dimension information exceeds a threshold, transmit a dimension anomaly signal to a predictive parcel damage mitigation system.

6. The apparatus of claim 1

Assignees

• United parcel service america inc

Inventors

• Goja Asheesh
• Almberg Eric

Classifications

• G06Q10/083 Primary

  Shipping · CPC title

• B64U2101/64

  for parcel delivery or retrieval · CPC title

• B64U2101/30

  for imaging, photography or videography · CPC title

• B64U10/16

  with five or more distinct rotor axes, e.g. octocopters · CPC title

• B64U30/26

  Ducted or shrouded rotors · CPC title