Image and object detection enhancement based on lighting profiles

Patent metadata

Field	Value
Publication number	US-11176647-B2
Application number	US-201916710636-A
Country	US
Kind code	B2
Filing date	Dec 11, 2019
Priority date	Dec 11, 2019
Publication date	Nov 16, 2021
Grant date	Nov 16, 2021

Abstract

Methods and systems may provide for technology to identify one or more light sources. The technology generates a light reflection profile associated with the one or more light sources. The light reflection profile is to predict one or more of reflection characteristics of light emitted from the one or more light sources or identify at least one characteristic of the one or more light sources. The technology further one or more of adjusts a first image based on the light reflection profile or identify one or more characteristics of a first object in the first image based on the light reflection profile.

First claim

I claim:

1. A vehicle comprising:
one or more cameras to capture one or more images including a first image; and
an image controller that includes logic to:
identify one or more light sources;
generate a light reflection profile associated with the one or more light sources, wherein the light reflection profile is to predict one or more of reflection characteristics of light emitted from the one or more light sources or identify at least one characteristic of the one or more light sources;
one or more of adjust the first image based on the light reflection profile or identify one or more characteristics of a first object in the first image based on the light reflection profile;
determine first light reflected from a first side of the first object;
determine second light reflected from a second side of the first object;
conduct a comparison of the first light reflected from the first side of the first object to the second light reflected from the second side of the first object; and
identify one or more characteristics of the first object based on the comparison,
wherein the first side of the first object is different from the second side of the first object.

2. The vehicle of claim 1 , wherein the logic is to:
generate the light reflection profile based on an identified position of a first light source of the one or more light sources;
determine reflected light reflected from the first object based on the first image; and
identify the one or more characteristics of the first object based on the determined reflected light and the light reflection profile.

3. The vehicle of claim 2 , wherein the one or more characteristics include a size of the first object, a height of the first object, a distance of the first object from the vehicle, a position of the first object relative to the vehicle and a direction of the first object relative to the vehicle.

4. The vehicle of claim 1 , wherein the logic is to:
identify one or more characteristics of a second object, wherein the one or more characteristics of the second object are to include at least a material of the second object;
generate the light reflection profile based on the one or more characteristics of the second object; and
adjust the first image based on the one or more characteristics of the second object in the light reflection profile.

5. The vehicle of claim 1 , wherein the logic is to:
identify an external light source based on the first image and the light reflection profile, wherein the external light source is absent in the first image.

6. The vehicle of claim 5 , wherein the logic is to:
identify one or more changes in characteristics of the light reflection profile;
determine a distance and a movement of the external light source based on the one or more changes; and
determine if another object has moved between the external light source and a reflectance area.

7. The vehicle of claim 1 , wherein the logic is to:
generate an astral body reflection profile; and
one or more of adjust the first image based on the astral body reflection profile or identify the one or more characteristics of the first object in the first image based on the astral body reflection profile.

8. The vehicle of claim 1 , wherein the logic is to:
identify weather related data; and
one or more of adjust the first image based on the weather related data or identify the one or more characteristics of the first object in the first image based on the weather related data.

9. At least one computer readable storage medium comprising a set of instructions, which when executed by an image controller of a vehicle, cause the image controller to:
identify one or more light sources;
generate a light reflection profile associated with the one or more light sources, wherein the light reflection profile is to predict one or more of reflection characteristics of light emitted from the one or more light sources or identify at least one characteristic of the one or more light sources;
one or more of adjust a first image based on the light reflection profile or identify one or more characteristics of a first object in the first image based on the light reflection profile;
determine first light reflected from a first side of the first object;
determine second light reflected from a second side of the first object;
conduct a comparison of the first light reflected from the first side of the first object to the second light reflected from the second side of the first object; and
identify the one or more characteristics of the first object based on the comparison,
wherein the first side of the first object is different from the second side of the first object.

10. The at least one computer readable storage medium of claim 9 , wherein the instructions, when executed, cause the image controller to:
generate the light reflection profile based on an identified position of a first light source of the one or more light sources;
determine reflected light reflected from the first object based on the first image; and
identify the one or more characteristics of the first object based on the determined reflected light and the light reflection profile.

11. The at least one computer readable storage medium of claim 10 , wherein the one or more characteristics include a size of the first object, a height of the first object, a distance of the first object from the vehicle, a position of the first object relative to the vehicle and a direction of the first object relative to the vehicle.

12. The at least one computer readable storage medium of claim 9 , wherein the instructions, when executed, cause the image controller to:
identify one or more characteristics of a second object, wherein the one or more characteristics of the second object are to include at least a material of the second object;
generate the light reflection profile based on the one or more characteristics of the second object; and
adjust the first image based on the one or more characteristics of the second object in the light reflection profile.

13. The at least one computer readable storage medium of claim 9 , wherein the instructions, when executed, cause the image controller to:
identify an external light source based on the first image and the light reflection profile, wherein the external light source is absent in the first image.

14. The at least one computer readable storage medium of claim 13 , wherein the instructions, when executed, cause the image controller to:
identify one or more changes in characteristics of the light reflection profile;
determine a distance and a movement of the external light source based on the changes; and
determine if another object has moved between the external light source and a reflectance area.

15. The at least one computer readable storage medium of claim 9 , wherein the instructions, when executed, cause the image controller to:
generate an astral body reflection profile; and
one or more of adjust the first image based on the astral body reflection profile or identify the one or more characteristics of the first object in the first image based on the astral body reflection profile.

16. The at least one computer readable storage medium of claim 9 , wherein the instructions, when executed, cause the image controller to:
identify weather related data; and
one or more of adjust the first image based on the weather related data or identify the one or more characteristics of the first object in the first image based on the weather related data.

17. A method of image analysis with an image controller of

Assignees

• Toyota Eng & Mfg North America

Inventors

• Auner David B

Classifications

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06T7/50

  Depth or shape recovery · CPC title

• G06T7/73

  using feature-based methods · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T5/009 Primary

  Physics · mapped topic