Method and System for Video-Based Positioning and Mapping
US-2020098135-A1 · Mar 26, 2020 · US
US11798293B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11798293-B2 |
| Application number | US-201916727435-A |
| Country | US |
| Kind code | B2 |
| Filing date | Dec 26, 2019 |
| Priority date | Dec 28, 2018 |
| Publication date | Oct 24, 2023 |
| Grant date | Oct 24, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A device, system and method for determining a position of a movable object on a two-dimensional surface obtains, via an image capture device attached to the movable object, at least one image of a portion of the two-dimensional surface. At one virtual marker is identified in at least one image, and a previously determined estimated position of the at least one virtual marker is retrieved. The previously determined estimated position determined from a combination of an image of at least one anchor point on the two-dimensional surface, the at least one anchor point defining a unique position on the two-dimensional surface, and odometry measurements based on at least two images of the two-dimensional surface. The position of the movable object on the two-dimensional surface is determined from the estimated position of the at least one virtual marker.
Opening claim text (preview).
What is claimed is: 1. A method for determining a position of a movable object on a two-dimensional surface, the method comprising: obtaining, via an image capture device attached to the movable object, at least one image of a portion of the two-dimensional surface; identifying in the at least one image at least one virtual marker; retrieving a previously determined estimated position of the at least one virtual marker, said previously determined estimated position of the at least one virtual marker determined from a combination of an image of at least one anchor point on the two-dimensional surface, the at least one anchor point defining a unique, pre-defined position spaced apart from the virtual marker and the position of the movable object on the two-dimensional surface, and odometry measurements based on at least two images of the two-dimensional surface; determining the position of the movable object on the two-dimensional surface from the estimated position of the at least one virtual marker; and sharing the estimated position of the at least one virtual marker with other movable objects operating on the two-dimensional surface. 2. The method according to claim 1 , comprising updating the estimated position of the at least one virtual marker based on position data related to the at least one virtual marker from at least one other movable object on the two-dimensional surface. 3. The method according to claim 1 , comprising prior to retrieving the previously determined estimated position of the at least one virtual marker, identifying at least one image of a plurality of images that includes an anchor point; determining an anchor position from the identified image of the anchor point; determining the estimated position of the at least one virtual marker based on the anchor position and the odometry measurements. 4. The method according to claim 3 , wherein identifying at least one image of the plurality of images that includes at least one virtual marker includes defining the at least one virtual marker from features of the two-dimensional surface. 5. The method according to claim 4 , wherein defining the at least one virtual marker from features of the two-dimensional surface includes defining the at least one virtual marker from variations in the two-dimensional surface, or from wear patterns in the two-dimensional surface, or from objects fixed to the two-dimensional surface. 6. The method according to claim 1 , wherein the odometry measurements are based on at least two different images of the at least one virtual marker to identify a change in position of the movable object relative to the anchor point. 7. The method according to claim 1 , comprising using homography to perform the odometry measurements. 8. The method according to claim 1 , wherein each anchor point is encoded with position data that defines a unique two-dimensional position on the two-dimensional surface. 9. A non-transitory computer-readable medium comprising computer executable instructions which when executed by a processor cause the processor to perform the steps according to claim 1 . 10. A movable object configured to travel along a prescribed two-dimensional surface, comprising: an image capture device; and a controller communicatively coupled to the image capture device and operative to receive image data therefrom, wherein the controller is configured to: obtain, via the image capture device, at least one image of a portion of the two-dimensional surface; identify in the at least one image at least one virtual marker; retrieve a previously determined estimated position of the at least one virtual marker, said previously determined estimated position of the at least one virtual marker determined from a combination of an image of at least one anchor point on the two-dimensional surface, the at least one anchor point defining a unique, pre-defined position distinct from the virtual marker and a position of the movable object on the two-dimensional surface, and odometry measurements based on at least two images of the two-dimensional surface; and determine the position of the movable object on the two-dimensional surface from the estimated position of the at least one virtual marker. 11. The movable object according to claim 10 , further comprising: a support structure including a plurality of wheels, wherein said image capture device is attached to said support structure; and a prime mover arranged on the support structure and drivingly coupled to the plurality of wheels to effect motion of the movable object. 12. The movable object according to claim 10 , wherein prior to retrieving the previously determined estimated position of the at least one virtual marker, the controller is configured to: identify at least one image of the plurality of images that includes an anchor point; determine an anchor position from the identified image of the anchor point; determine the estimated position of the at least one virtual marker based on the anchor position and the odometry measurements; and store the estimated position of the at least one virtual marker. 13. The movable object according to claim 10 , wherein the controller is configured to base the odometry measurements on at least two different images of the at least one virtual marker to identify a change in position of the movable object relative to the anchor point. 14. The movable object according to claim 10 , wherein the controller is configured to define the at least one virtual marker from features of the two-dimensional surface. 15. The movable object according to claim 14 , wherein the controller is configured to define the at least one virtual marker from variations in the two-dimensional surface, from wear patterns in the two-dimensional surface, or from objects fixed to the two-dimensional surface. 16. A system for navigating a movable object on a prescribed two-dimensional surface, comprising: at least one anchor point arrangeable on the two-dimensional surface, the at least one anchor point including information defining a unique anchor position of the anchor point on the two-dimensional surface; and the movable object according to claim 10 . 17. The system according to claim 16 , wherein the at least one anchor point comprises at least one of a label attachable to the two-dimensional surface, an image projectable onto the two-dimensional surface, an image painted on the two-dimensional surface, a QR code, a bar code or a natural feature formed on the two-dimensional surface. 18. A system for navigating a movable object on a prescribed two-dimensional surface, comprising: at least one anchor point arrangeable on the two-dimensional surface, the at least one anchor point including information defining a unique anchor position of the anchor point on the two-dimensional surface; and a plurality of movable objects according to claim 10 , wherein each movable object of the plurality of movable objects is configured to share locations of the at least one virtual marker with other movable objects of the plurality of movable objects. 19. A method for defining a position of at least one virtual marker on a prescribed two-dimensional surface, the method comprising: obtaining, via an image capture device attached to a movable object traveling on the two-dimensional surface, a plurality of images of a portion of the two-dimensional surface; identifying at least one image of the plurality of images that includes an anchor point that defines a unique, pre-defined positi
using dead reckoning · CPC title
Optical signals · CPC title
of freight · CPC title
Industrial sites, e.g. warehouses or factories · CPC title
Land vehicles · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.