IP Library › Granted Patent US 11,042,996
Granted Patent B2
US 11,042,996 · App. 16/439,000 · Granted Jun 22, 2021

Recognition apparatus

Inventors: Takahisa Yokoyama (Kariya, JP); Kensuke Yokoi (Kariya, JP); Tatsuru Kuwabara (Kariya, JP)
Assignee: DENSO CORPORATION
G06T7/292G06K9/00288G07C5/0816
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,042,996
App. No.
16/439,000
Granted
Jun 22, 2021
Kind
B2
Abstract

A recognition apparatus is provided which includes an input section that receives image information from a front camera and a rear camera, and a calculation section that performs a forward recognition process that is a recognition process targeting the image information from the front camera received by the input section and a rearward recognition process that is a recognition process targeting the image information from the rear camera received by the input section. The calculation section includes an acquisition section that acquires first information representing whether an own vehicle is in a state of moving forward or a state of moving rearward and second information representing a traveling condition of the own vehicle, and a process selection section that selects processes to be performed as the forward recognition process and the rearward recognition process, based on the first and second information acquired by the acquisition section.

Claims (75)

1. A recognition apparatus, comprising:

an input section that receives image information from a front camera and a rear camera; and

a calculation section that performs a forward recognition process that is a recognition process targeting the image information from the front camera received by the input section and a rearward recognition process that is a recognition process targeting the image information from the rear camera received by the input section, wherein

the calculation section includes:

an acquisition section that acquires first information representing whether an own vehicle is in a state of moving forward or a state of moving rearward and second information representing a traveling condition of the own vehicle; and

a process selection section that selects processes to be performed as the forward recognition process and the rearward recognition process, based on the first and second information acquired by the acquisition section, wherein

the acquisition section acquires information representing a speed of the own vehicle as the information representing the traveling condition, and

in a case where the speed of the own vehicle is low while the own vehicle is moving forward, the process selection section increases a number of the processes to be performed as the rearward recognition process compared with a case where the speed of the own vehicle is high.

2. The recognition apparatus according to claim 1 , wherein

the calculation section recognizes a predetermined plurality types of recognition targets based on the image information, and

the process selection section selects a process for recognizing a recognition target included in the plurality types of recognition targets among processes included in the forward recognition process and the rearward recognition process, based on the information acquired by the acquisition section.

3. The recognition apparatus according to claim 2 , wherein

the recognition targets are classified with reference to whether the recognition targets are moving, and

the process selection section selects a process for recognizing a recognition target that is moving in priority to a process for recognizing a recognition target that is not moving.

4. The recognition apparatus according to claim 2 , wherein

the recognition targets are classified with reference to distances from the own vehicle, and

the process selection section selects a process for recognizing a recognition target whose distance from the own vehicle is short in priority to a process for recognizing a recognition target whose distance from the own vehicle is long.

5. The recognition apparatus according to claim 1 , wherein

the calculation section recognizes a recognition target by pattern matching based on dictionary information that is previously stored, and

in the forward recognition process and the rearward recognition process, a recognition target ahead of the own vehicle and a recognition target behind the own vehicle are recognized by using the same dictionary information.

6. The recognition apparatus according to claim 1 , wherein

the calculation section includes an acquisition section that causes a display unit to display at least one of a forward image captured by the front camera and a rearward image captured by the rear camera, the display unit determines an image to be displayed based on information representing whether the own vehicle is in a state of moving forward or a state of moving rearward and information representing the traveling condition of the own vehicle, and in a case where the forward image and the rearward image are displayed together, part of the forward image and part of the rearward image are displayed.

7. The recognition apparatus according to claim 1 , wherein

the speed of the own vehicle is low for a state in which the speed of the own vehicle is less than a predetermined speed, and

the speed of the own vehicle is high for a state in which the speed of the own vehicle is greater than the predetermined speed.

8. A recognition apparatus, comprising:

an input section that receives image information from a front camera and a rear camera; and

a calculation section that performs a forward recognition process that is a recognition process targeting the image information from the front camera received by the input section and a rearward recognition process that is a recognition process targeting the image information from the rear camera received by the input section, wherein

the calculation section includes:

an acquisition section that acquires first information representing whether an own vehicle is in a state of moving forward or a state of moving rearward and second information representing a traveling condition of the own vehicle; and

a process selection section that selects processes to be performed as the forward recognition process and the rearward recognition process, based on the first and second information acquired by the acquisition section, wherein

the acquisition section acquires information representing a speed of the own vehicle as the information representing the traveling condition, and

in a case where the speed of the own vehicle is low while the own vehicle is moving forward, the process selection section decreases a number of processes to be performed as the forward recognition process compared with a case where the speed of the own vehicle is high.

9. The recognition apparatus according to claim 8 , wherein

the speed of the own vehicle is low for a state in which the speed of the own vehicle is less than a predetermined speed, and

the speed of the own vehicle is high for a state in which the speed of the own vehicle is greater than the predetermined speed.

10. The recognition apparatus according to claim 8 , wherein

the calculation section recognizes a predetermined plurality types of recognition targets based on the image information, and

the process selection section selects a process for recognizing a recognition target included in the plurality types of recognition targets among processes included in the forward recognition process and the rearward recognition process, based on the information acquired by the acquisition section.

11. The recognition apparatus according to claim 10 , wherein

the recognition targets are classified with reference to whether the recognition targets are moving, and

the process selection section selects a process for recognizing a recognition target that is moving in priority to a process for recognizing a recognition target that is not moving.

12. The recognition apparatus according to claim 10 , wherein

the recognition targets are classified with reference to distances from the own vehicle, and

the process selection section selects a process for recognizing a recognition target whose distance from the own vehicle is short in priority to a process for recognizing a recognition target whose distance from the own vehicle is long.

13. The recognition apparatus according to claim 8 , wherein

the calculation section recognizes a recognition target by pattern matching based on dictionary information that is previously stored, and

in the forward recognition process and the rearward recognition process, a recognition target ahead of the own vehicle and a recognition target behind the own vehicle are recognized by using the same dictionary information.

14. The recognition apparatus according to claim 8 , wherein

the calculation section includes an acquisition section that causes a display unit to display at least one of a forward image captured by the front camera and a rearward image captured by the rear camera, the display unit determines an image to be displayed based on information representing whether the own vehicle is in a state of moving forward or a state of moving rearward and information representing the traveling condition of the own vehicle, and in a case where the forward image and the rearward image are displayed together, part of the forward image and part of the rearward image are displayed.

15. A recognition apparatus, comprising:

an input section that receives image information from a front camera and a rear camera; and

a calculation section that performs a forward recognition process that is a recognition process targeting the image information from the front camera received by the input section and a rearward recognition process that is a recognition process targeting the image information from the rear camera received by the input section, wherein

the calculation section includes:

an acquisition section that acquires first information representing whether an own vehicle is in a state of moving forward or a state of moving rearward and second information representing a traveling condition of the own vehicle; and

a process selection section that selects processes to be performed as the forward recognition process and the rearward recognition process, based on the first and second information acquired by the acquisition section, wherein

the acquisition section acquires information representing a place where the own vehicle travels as information representing the traveling condition, and

the process selection section selects the processes to be performed as the forward recognition process and the rearward recognition process according to the place where the own vehicle travels.

16. The recognition apparatus according to claim 15 , wherein

the speed of the own vehicle is low for a state in which the speed of the own vehicle is less than a predetermined speed, and

the speed of the own vehicle is high for a state in which the speed of the own vehicle is greater than the predetermined speed.

17. The recognition apparatus according to claim 15 , wherein

the calculation section recognizes a predetermined plurality types of recognition targets based on the image information, and

the process selection section selects a process for recognizing a recognition target included in the plurality types of recognition targets among processes included in the forward recognition process and the rearward recognition process, based on the information acquired by the acquisition section.

18. The recognition apparatus according to claim 17 , wherein

the recognition targets are classified with reference to whether the recognition targets are moving, and

the process selection section selects a process for recognizing a recognition target that is moving in priority to a process for recognizing a recognition target that is not moving.

19. The recognition apparatus according to claim 17 , wherein

the recognition targets are classified with reference to distances from the own vehicle, and

the process selection section selects a process for recognizing a recognition target whose distance from the own vehicle is short in priority to a process for recognizing a recognition target whose distance from the own vehicle is long.

20. The recognition apparatus according to claim 15 , wherein

the calculation section recognizes a recognition target by pattern matching based on dictionary information that is previously stored, and

in the forward recognition process and the rearward recognition process, a recognition target ahead of the own vehicle and a recognition target behind the own vehicle are recognized by using the same dictionary information.

21. The recognition apparatus according to claim 15 , wherein

the calculation section includes an acquisition section that causes a display unit to display at least one of a forward image captured by the front camera and a rearward image captured by the rear camera, the display unit determines an image to be displayed based on information representing whether the own vehicle is in a state of moving forward or a state of moving rearward and information representing the traveling condition of the own vehicle, and in a case where the forward image and the rearward image are displayed together, part of the forward image and part of the rearward image are displayed.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 9, 2019
From: YOKOYAMA, TAKAHISA; YOKOI, KENSUKE; KUWABARA, TATSURU
To: DENSO CORPORATION
Reel/Frame 050016/0529 →
Priority Claims (1)
JP JP2016-241223 · Dec 13, 2016 · national
Continuity (2)
Continuation PCTJP2017042416 · Nov 27, 2017
Related Publication 20190347810A1 · Nov 14, 2019
Cited By (1)
US 12,623,681