Apparatus and methods for computerized object identification

Patent metadata

Field	Value
Publication number	US-2020175640-A1
Application number	US-202016783688-A
Country	US
Kind code	A1
Filing date	Feb 6, 2020
Priority date	Oct 24, 2014
Publication date	Jun 4, 2020
Grant date	—

Abstract

Apparatus and methods for identification of a coded pattern visible to a computerized imaging apparatus while invisible or inconspicuous to human eyes. A pattern and/or marking may serve to indicate identity of an object, and/or the relative position of the pattern to a viewer. While some solutions exist for identifying patterns (for example, QR codes), they may be visually obtrusive to a human observer due to visual clutter. In exemplary implementations, apparatus and methods are capable of generating patterns with sufficient structure to be used for either discrimination or some aspect of localization, while incorporating spectral properties that are more aesthetically acceptable such as being: a) imperceptible or subtle to the human observer and/or b) aligned to an existing acceptable visual form, such as a logo. In one variant, a viewer comprises an imaging system comprised as a processor and laser scanner, or camera, or moving photodiode.

First claim

What is claimed is:

1 . A non-transitory computer-readable storage medium, comprising processor-executable instructions for controlling, in response the instructions, an autonomous vehicle to traverse a portion of an operational environment of the autonomous vehicle based on object tracking by:
obtaining a first image of a video captured by an imaging device of the autonomous vehicle; processing the first image to obtain first object tracking data identifying a portion of the first image based on a characteristic of a color of the portion of the first image, wherein the portion of the first image corresponds to an object captured by the first image, and wherein the first image includes at least one other portion; autonomously controlling an orientation of the autonomous vehicle based on the first object tracking data; obtaining a second image, the second image subsequent to the first image in the video; processing the second image to obtain second object tracking data identifying a portion of the second image based on the characteristic of the color of the portion of the second image, wherein the portion of the second image corresponds to the object captured by the second image, and wherein the second image includes at least one other portion; and autonomously controlling the orientation of the autonomous vehicle based on the second object tracking data.

2 . The non-transitory computer-readable storage medium of claim 1 , wherein processing the first image includes processing the image based on pixel intensity for at least two pixels of the first image.

3 . The non-transitory computer-readable storage medium of claim 1 , wherein processing the first image includes:
obtaining data identifying a region within the first image; and obtaining the first object tracking data based on the region.

4 . The non-transitory computer-readable storage medium of claim 1 , wherein:
the characteristic includes a first shape formed by the object in the first image; autonomously controlling the orientation of the autonomous vehicle based on the first object tracking data includes autonomously controlling the orientation of the autonomous vehicle in response to identifying the first shape; the characteristic includes a second shape formed by the object in the second image; and autonomously controlling the orientation of the autonomous vehicle based on the second object tracking data includes autonomously controlling the orientation of the autonomous vehicle in response to identifying the second shape.

5 . The non-transitory computer-readable storage medium of claim 4 , wherein:
autonomously controlling the orientation of the autonomous vehicle based on the first object tracking data includes autonomously controlling a distance of the autonomous vehicle from the object; and autonomously controlling the orientation of the autonomous vehicle based on the second object tracking data includes autonomously controlling the autonomous vehicle independent of the object.

6 . A method of autonomous vehicle control based on object tracking, the method comprising:
obtaining an image; processing the image to obtain object tracking data identifying a portion of the image based on a characteristic of a color of the portion of the image, wherein the portion of the image corresponds to an object captured by the image, and wherein the image includes at least one other portion; and autonomously controlling an orientation of the autonomous vehicle relative to the object based on the object tracking data.

7 . The method of claim 6 , wherein:
obtaining the image includes obtaining the image by an image processor from an imaging device of the autonomous vehicle via a computing communication link.

8 . The method of claim 6 , wherein processing the image includes processing the image based on pixel intensity for at least two pixels of the image.

9 . The method of claim 6 , wherein autonomously controlling the orientation of the autonomous vehicle includes autonomously controlling a distance of the autonomous vehicle from the object.

10 . The method of claim 6 , wherein processing the image includes:
obtaining data identifying a region within the image; and obtaining the object tracking data based on the region.

11 . The method of claim 10 , wherein the region is rectangular.

12 . The method of claim 6 , wherein the characteristic includes a shape formed by the object.

13 . The method of claim 12 , wherein autonomously controlling the orientation of the autonomous vehicle includes autonomously controlling the orientation of the autonomous vehicle in response to identifying the shape.

14 . The method of claim 6 , wherein:
the image is a first image of a video captured by the imaging device, the method further comprising: obtaining a second image, the second image subsequent to the first image in the video; processing the second image to obtain second object tracking data identifying a portion of the second image based on the characteristic of the color of the portion of the second image, wherein the portion of the second image corresponds to the object captured by the second image, and wherein the second image includes at least one other portion; and autonomously controlling the orientation of the autonomous vehicle relative to the object based on the second object tracking data.

15 . A system comprising:
an image processor, the image processor including a first communication device; and an autonomous vehicle, the autonomous vehicle including:
a second communication device; and
an image capture device;
wherein:
the image capture device is configured to obtain an image;
the first communication device is configured to communicate the image to the second communication device via a computing communication link;
the image processor is configured to process the image to obtain object tracking data identifying a portion of the image based on a characteristic of a color of the portion of the image, wherein the portion of the image corresponds to an object captured by the image, and wherein the image includes at least one other portion; and
the autonomous vehicle is configured to control an orientation of the autonomous vehicle relative to the object based on the object tracking data.

16 . The system of claim 15 , wherein the image processor is configured to process the image based on pixel intensity for at least two pixels of the image.

17 . The system of claim 15 , wherein the autonomous vehicle is configured to control the orientation of the autonomous vehicle by autonomously controlling a distance of the autonomous vehicle from the object.

18 . The system of claim 15 , wherein the image processor is configured to process the image by:
obtaining data identifying a region within the image; and obtaining the object tracking data based on the region.

19 . The system of claim 15 , wherein:
the image is a first image of a video captured by the image capture device; the image capture device is configured to obtain a second image, the second image subsequent to the first image in the video; the image processor is configured to process the second image to obtain second object tracking data identifying a portion of the second image based on the characteristic of the color of the portion of the second image, wherein the portion of the second image corresponds to the object captured by the second image, and wherein the second image includes at least one other portion; and the autonomous vehicle is configur

Assignees

• Gopro Inc

Inventors

• Meier Philip
• Fisher Dimitry
• Roth Chance
• Hypnarowski Steven

Classifications

• G06T1/0014 Primary

  Image feed-back for automatic industrial control, e.g. robot with camera (robots B25J19/023) · CPC title

• G06K9/4671

  Physics · mapped topic

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title