Pedestrian determination method and determination device

• US 10,503,985 B2
• Filed: 11/28/2016
• Issued: 12/10/2019
• Est. Priority Date: 01/22/2016
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Gokan, Toshimichi, Inoue, Takuya, Suzuki, Tatsuya, Tamaki, Kazuo
• Primary Examiner(s): Frejd, Russell
• Application Number:
  US16/071,501
• Publication Number:
  US 20190034742A1
• Time in Patent Office: 1,107 Days
• CPC Class Codes: B60T 7/12 for automatic initiation; for initiation not subject to will of driver or passenger limiting speed of vehicles other than rail vehicles B60K31/00
• CPC Class Codes: G01S 13/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S13/46
• CPC Class Codes: G01S 13/723 by using numerical data
• CPC Class Codes: G01S 13/86 Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 13/93 for anti-collision purposes
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 2013/9323 Alternative operation using light waves
• CPC Class Codes: G01S 2013/93271 in the front of the vehicles
• CPC Class Codes: G01S 7/411 Identification of targets based on measurements of radar reflectivity G01S7/415 takes precedence
• CPC Class Codes: G06T 2207/10044 Radar image
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08G 1/09 Arrangements for giving variable traffic instructions railroad crossing signals B61L; reflectors E01F, G08B; indicating arrangements for variable information by selection or combination of individual elements G09F9/00
• CPC Class Codes: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08

Abstract

A host vehicle is provided with external environment recognition sensors that acquire forward information to determine that a pedestrian is present in a forward position of the host vehicle using the external environment recognition sensors. In this pedestrian determination method, a front camera and a millimeter wave radar are provided as the external environment recognition sensors. When a pedestrian candidate is detected in a forward position of the host vehicle based on an image signal from the front camera, a matching area is set with the position of the detected pedestrian candidate as the center point. When the position of the object that is closest to the pedestrian candidate from among the plurality of objects detected by reflected waves from the millimeter wave radar is within the matching area thereby establishing a match, the pedestrian candidate is determined to be a pedestrian.

Claims

1. A pedestrian determination method that is provided with external environment recognition sensors that obtain forward information of a host vehicle and that uses the external environment recognition sensors to determine that a pedestrian is present in a forward position of the host vehicle, the method comprising:

providing a camera and a radar as the external environment recognition sensors;

setting a matching area based on a position of a pedestrian candidate that is detected as a center point, upon detecting the pedestrian candidate in the forward position of the host vehicle based on an image signal from the camera; and

determining the pedestrian candidate to be a pedestrian when a position of an object closest to the pedestrian candidate from among a plurality of objects detected by reflected waves from the radar is present within the matching area and a match is established; and

expanding the matching area when the position of the pedestrian candidate and the position of the object are in a same direction.

2. The pedestrian determination method according to claim 1, wherein

the match has been determined to be established when a time during which an object that is closest to the pedestrian candidate is present within the matching area for a predetermined period of time or more.

3. The pedestrian determination method according to claim 1, wherein

the matching area is divided into a plurality of concentric regions by a plurality of score lines centered around the pedestrian candidate, and a score map is configured such that positive side scores that increase with decreasing distance to the center point are assigned to an area inside of an area boundary score line, and a negative side score is assigned to an area outside of the area boundary score line, and

when a value obtained by adding a score per one control cycle for carrying out the matching determination becomes greater than or equal to a predetermined threshold value, the pedestrian candidate is determined to be a pedestrian by establishing a match.

4. The pedestrian determination method according to claim 1, wherein

when an angular difference between a detection angle of a pedestrian candidate detected by the camera and a detection angle of an object detected by the radar is a predetermined value or smaller, the matching area that is used when the angular difference exceeds the predetermined value is switched to a matching area that is expanded in a longitudinal direction, which is the longitudinal direction of the host vehicle.

5. The pedestrian determination method according to claim 1, wherein

a first matching area for carrying out matching determination when the host vehicle and a pedestrian are at a first distance, and a second matching area for carrying out matching determination when the host vehicle and a pedestrian are at a second distance, which is less than the first distance, and having a smaller area than the first matching area, are set as the matching areas.

6. The pedestrian determination method according to claim 5, wherein

the method is applied to an automatic brake control system, in which, upon determining that the host vehicle and a pedestrian could come in contact, preliminary braking by using slow braking is carried out, and if the possibility of contact increases during the preliminary braking, main braking by sudden braking is carried out, thereby preventing contact between the host vehicle and the pedestrian,

the first matching area is a preliminary braking matching area that is used for determining pedestrians when carrying out the preliminary braking, and

the second matching area is a main braking matching area that is used for determining pedestrians when carrying out the main braking.

7. A pedestrian determination device comprising:

external environment recognition sensors that acquire forward information for a host vehicle; and

a matching determination processing unit that determines that a pedestrian is present in a forward position of the host vehicle using the external environment recognition sensors;

the external environment recognition sensors including a camera and a radar; and

the matching determination processing unit carries out a process

to set a matching area based on a position of a pedestrian candidate that is detected as the center point, upon detecting the pedestrian candidate in the forward position of the host vehicle based on an image signal from the camera, and

to determine the pedestrian candidate to be a pedestrian, when the position of an object that is closest to the pedestrian candidate from among a plurality of objects detected by reflected waves from the radar is within the matching area and a match is established, and

to expand the matching area when the position of the pedestrian candidate and the position of the object are in a same direction.

8. A pedestrian determination method that is provided with external environment recognition sensors that obtain forward information of a host vehicle, and that uses the external environment recognition sensors to determine that a pedestrian is present in a forward position of the host vehicle, the method comprising:

providing a camera and a radar as the external environment recognition sensors;

setting a matching area based on a position of a pedestrian candidate that is detected, upon detecting the pedestrian candidate in the forward position of the host vehicle based on an image signal from the camera;

setting, as the matching area, a first matching area for carrying out a matching determination when the host vehicle and a pedestrian candidate are separated by a first distance, and a second matching area for carrying out a matching determination when the host vehicle and a pedestrian candidate are separated by a second distance, which is shorter than the first distance, having a smaller area than the first matching area; and

determining the pedestrian candidate to be a pedestrian, when the position of an object closest to the pedestrian candidate from among a plurality of objects detected by reflected waves from the radar is present within the matching area and a match is established.