Semantically aware keypoint matching

Patent metadata

Field	Value
Publication number	US-12183087-B2
Application number	US-202318489687-A
Country	US
Kind code	B2
Filing date	Oct 18, 2023
Priority date	Apr 14, 2020
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

A method for keypoint matching performed by a semantically aware keypoint matching model includes generating a semanticly segmented image from an image captured by a sensor of an agent, the semanticly segmented image associating a respective semantic label with each pixel of a group of pixels associated with the image. The method also includes generating a set of augmented keypoint descriptors by augmenting, for each keypoint of the set of keypoints associated with the image, a keypoint descriptor with semantic information associated with one or more pixels, of the semantically segmented image, corresponding to the keypoint. The method further includes controlling an action of the agent in accordance with identifying a target image having one or more first augmented keypoint descriptors that match one or more second augmented keypoint descriptors of the set of augmented keypoint descriptors.

First claim

What is claimed is:

1. A method for keypoint matching performed by a semantically aware keypoint matching model, the method comprising:
generating a semanticly segmented image from an image captured by a sensor of an agent, the semanticly segmented image associating a respective semantic label with each pixel of a group of pixels associated with the image;
generating a set of augmented keypoint descriptors by augmenting, for each keypoint of the set of keypoints associated with the image, a keypoint descriptor with semantic information associated with one or more pixels, of the semanticaly segmented image, corresponding to the keypoint; and
controlling an action of the agent in accordance with identifying a target image having one or more first augmented keypoint descriptors that match one or more second augmented keypoint descriptors of the set of augmented keypoint descriptors.

2. The method of claim 1 , further comprising identifying the one or more first augmented keypoint descriptors of the target image matching the one or more second augmented keypoint descriptors of the image based on a nearest neighbor matching function.

3. The method of claim 2 , further comprising biasing the matching of the one or more first augmented keypoint descriptors of the target image and the one or more second augmented keypoint descriptors toward two or more descriptors having matching semantic labels.

4. The method of claim 1 , further comprising identifying a current location of the agent based on the target image, wherein controlling the action of the agent comprises navigating to a new location from the current location.

5. The method of claim 1 , wherein:
the target image is identified from a plurality of stored images; and
each one of the stored images is associated with one or more augmented keypoint descriptors.

6. The method of claim 1 , wherein the agent is an autonomous vehicle or a semi-autonomous vehicle.

7. The method of claim 1 , wherein the image is a monocular image.

8. An apparatus for keypoint matching performed by a semantically aware keypoint matching model, comprising:
one or more processors; and
one or more memories coupled with the one or more processors and storing instructions operable, when executed by the one or more processors, to cause the apparatus to:
generate a semanticly segmented image from an image captured by a sensor of an agent, the semanticly segmented image associating a respective semantic label with each pixel of a group of pixels associated with the image;
generate a set of augmented keypoint descriptors by augmenting, for each keypoint of the set of keypoints associated with the image, a keypoint descriptor with semantic information associated with one or more pixels, of the semanticaly segmented image, corresponding to the keypoint; and
control an action of the agent in accordance with identifying a target image having one or more first augmented keypoint descriptors that match one or more second augmented keypoint descriptors of the set of augmented keypoint descriptors.

9. The apparatus of claim 8 , wherein execution of the instructions further cause the apparatus to identify the one or more first augmented keypoint descriptors of the target image matching the one or more second augmented keypoint descriptors of the image based on a nearest neighbor matching function.

10. The apparatus of claim 9 , wherein execution of the instructions further cause the apparatus to bias the matching of the one or more first augmented keypoint descriptors of the target image and the one or more second augmented keypoint descriptors toward two or more descriptors having matching semantic labels.

11. The apparatus of claim 8 , wherein execution of the instructions further cause the apparatus to identify a current location of the agent based on the target image, wherein controlling the action of the agent comprises navigating to a new location from the current location.

12. The apparatus of claim 8 , wherein:
the target image is identified from a plurality of stored images; and
each one of the stored images is associated with one or more augmented keypoint descriptors.

13. The apparatus of claim 8 , wherein the agent is an autonomous vehicle or a semi-autonomous vehicle.

14. The apparatus of claim 8 , wherein the image is a monocular image.

15. A non-transitory computer-readable medium having program code recorded thereon for keypoint matching performed by a semantically aware keypoint matching model, the program code executed by a processor and comprising:
program code to generate a semanticly segmented image from an image captured by a sensor of an agent, the semanticly segmented image associating a respective semantic label with each pixel of a group of pixels associated with the image;
program code to generate a set of augmented keypoint descriptors by augmenting, for each keypoint of the set of keypoints associated with the image, a keypoint descriptor with semantic information associated with one or more pixels, of the semanticaly segmented image, corresponding to the keypoint; and
program code to control an action of the agent in accordance with identifying a target image having one or more first augmented keypoint descriptors that match one or more second augmented keypoint descriptors of the set of augmented keypoint descriptors.

16. The non-transitory computer-readable medium of claim 15 , wherein the program code further comprises program code to identify the one or more first augmented keypoint descriptors of the target image matching the one or more second augmented keypoint descriptors of the image based on a nearest neighbor matching function.

17. The non-transitory computer-readable medium of claim 16 , wherein the program code further comprises program code to bias the matching of the one or more first augmented keypoint descriptors of the target image and the one or more second augmented keypoint descriptors toward two or more descriptors having matching semantic labels.

18. The non-transitory computer-readable medium of claim 15 , wherein the program code further comprises program code to identify a current location of the agent based on the target image, wherein controlling the action of the agent comprises navigating to a new location from the current location.

19. The non-transitory computer-readable medium of claim 15 , wherein:
the target image is identified from a plurality of stored images; and
each one of the stored images is associated with one or more augmented keypoint descriptors.

20. The non-transitory computer-readable medium of claim 15 , wherein the agent is an autonomous vehicle or a semi-autonomous vehicle.

Assignees

• Toyota Res Inst Inc

Inventors

• Tang Jiexiong
• Ambrus Rares Andrei
• Guizilini Vitor
• Gaidon Adrien David

Classifications

• G05D1/243

  Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals (using passive navigation aids external to the vehicle G05D1/244; using signals from positioning sensors located off-board the vehicle G05D1/249) · CPC title

• G05D2101/10

  using artificial intelligence [AI] techniques · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• G05D1/0221

  involving a learning process · CPC title

• G05D1/0246

  using a video camera in combination with image processing means · CPC title