Photo instructions and confirmation

Patent metadata

Field	Value
Publication number	US-12008813-B2
Application number	US-202217897778-A
Country	US
Kind code	B2
Filing date	Aug 29, 2022
Priority date	Aug 29, 2022
Publication date	Jun 11, 2024
Grant date	Jun 11, 2024

Abstract

Computer program products, methods, systems, apparatus, and computing entities are provided for optimizing package delivery and confirmation are disclosed. In one embodiment, the system's processors accesses a first image of an assigned delivery location captured by a first computing device. The first image comprises an annotation indicating a specific location at the assigned delivery location for delivery of a parcel. At a display device of a second computing device, a real-time image stream comprising the annotation is captured by a camera of the second computing device is displayed. The annotation is overlaid within the real-time image stream based on comparing the first image received from the first computing device to the real-time image stream. The system further captures, from the real-time image stream, a second image when the parcel is positioned at the specific location based on the annotation overlaid within the real-time image stream.

First claim

What is claimed is:

1. A system for optimizing package delivery and confirmation, the system comprising:
one or more processors; and
one or more computer storage devices storing computer-useable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
accessing a first image of an assigned delivery location captured by a first computing device, wherein the first image of the assigned delivery location comprises an annotation indicating a specific location at the assigned delivery location for delivery of a parcel;
displaying, at a display device of a second computing device, a real-time image stream captured by a camera of the second computing device, wherein the real-time image stream comprises the annotation, the annotation being overlaid within the real-time image stream based on comparing the first image received from the first computing device to the real-time image stream; and
capturing, from the real-time image stream, a second image when the parcel is positioned at the specific location based on the annotation overlaid within the real-time image stream.

2. The system of claim 1 , wherein the operations further comprise determining a location of the second computing device while the real-time image stream is being captured, wherein the second image is captured from the real-time data stream based on the location of the second computing device relative to the assigned delivery location.

3. The system of claim 1 , wherein the operations further comprise:
receiving a first location of the first computing device determined at the time the first image is captured;
determining a second location of the second computing device while the real-time image stream is being captured; and
providing, at the display device of the second computing device, guidance instructions indicating a direction from the second location of the second computing device to the first location of the first computing device.

4. The system of claim 1 , wherein the operations further comprise identifying the parcel is positioned at the specific location, as indicated by the annotation, by identifying the parcel using an object recognition model, wherein the second image is automatically captured from the real-time image stream based on identifying the parcel is positioned at the specific location.

5. The system of claim 1 , wherein the operations further comprise identifying, at the specific location, as indicated by the annotation, machine readable indicia affixed to the parcel, the machine readable indicia being usable by the second computing device to determine a delivery location for the parcel, wherein the second image is automatically captured from the real-time image stream based on the determined delivery location for the parcel matching the assigned delivery location associated with the first image.

6. The system of claim 1 , wherein the first image received from the first computing device is compared to the real-time image stream using a convolutional neural network.

7. The system of claim 1 , wherein the annotation comprises a boundary marker, the boundary marker delineating the specific location at the assigned delivery location, and wherein the second image is captured from the real-time image stream when the parcel is positioned within the boundary marker.

8. The system of claim 1 , wherein the annotation comprises human readable text.

9. A computer implemented method for optimizing package delivery and confirmation, the method comprising:
receiving an annotation indicating a specific location at an assigned delivery location for delivery of a parcel, the annotation being determined from a first image of the assigned delivery location captured by a first computing device, wherein the first image of the assigned delivery location is annotated at the first computing device;
displaying, at a display device of a second computing device, the annotation indicating the specific location, the annotation being overlaid on a real-time image stream captured by a camera of the second computing device, wherein the annotation indicates the assigned delivery location; and
capturing, from the real-time image stream, a second image from the real-time image stream, the second image comprising the parcel positioned at the specific location based on the annotation overlaid within the real-time image stream.

10. The method of claim 9 , further comprising determining a location of the second computing device while the real-time image stream is being captured, wherein the second image is captured from the real-time data stream based on the location of the second computing device relative to the assigned delivery location.

11. The method of claim 9 , further comprising:
receiving a first location of the first computing device determined at the time the first image is captured;
determining a second location of the second computing device while the real-time image stream is being captured; and
providing, at the display device of the second computing device, guidance instructions indicating a direction from the second location of the second computing device to the first location of the first computing device.

12. The method of claim 9 , further comprising identifying the parcel is positioned at the specific location, as indicated by the annotation, by identifying the parcel using an object recognition model, wherein the second image is automatically captured from the real-time image stream based on identifying the parcel is positioned at the specific location.

13. The method of claim 12 , wherein the object recognition model is a convolutional neural network trained to identify parcels.

14. The method of claim 9 , further comprising identifying, at the specific location, as indicated by the annotation, machine readable indicia affixed to the parcel, the machine readable indicia being usable by the second computing device to determine a delivery location for the parcel, wherein the second image is automatically captured from the real-time image stream based on the determined delivery location for the parcel matching the assigned delivery location associated with the first image.

15. The method of claim 9 , wherein the annotation comprises a boundary marker, the boundary marker delineating the specific location at the assigned delivery location, and wherein the second image is captured from the real-time image stream when the parcel is positioned within the boundary marker.

16. The method of claim 15 , further comprising detecting the parcel is positioned within the boundary marker using an object recognition model, wherein the second image is automatically captured in response to detecting the parcel is positioned within the boundary marker.

17. The method of claim 9 , wherein the annotation comprises human readable text.

18. One or more non-transitory computer storage media storing computer readable instructions thereon that, when executed by a processor, cause the processor to perform operations of a method for optimizing package delivery and confirmation, the operations comprising:
receiving a first image of an assigned delivery location captured by a first computing device, wherein the first image of the assigned delivery location comprises an annotation indicating a specific location at the assigned delivery location for delivery of a parcel;
communicating, to a second computing device, the annotation indicating the specific location, wherein the annotation is overlaid on a real-time image stream captured by a camera of

Assignees

• United parcel service america inc

Inventors

• Carder David
• Fannon Ryan
• Mccauley William

Classifications

• G06V20/70

  Labelling scene content, e.g. deriving syntactic or semantic representations · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V20/20

  in augmented reality scenes · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T2207/30204

  Marker · CPC title