OBJECT RECOGNITION DEVICE

• US 20180005056A1
• Filed: 09/12/2017
• Published: 01/04/2018
• Est. Priority Date: 03/28/2011
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: MATSUBARA, Toshiyuki
• Granted Patent: US 10,614,322 B2
• Time in Patent Office: Days
• 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: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

In an object recognition device, a reliability setting unit sets object presence reliability indicating the reliability of whether or not an object is present with respect to the surrounding area of a host vehicle. Then, a grouping unit groups the reflection points based on the object presence reliability in the area between the reflection points. For this reason, for example, even though two objects are adjacent to each other, in a case where the object presence reliability in the area between the reflection points of one object and the reflection points of the other object is low, the reflection points of the two objects can be separately grouped without being grouped into a single group. As a result, since it is possible to avoid mistakenly recognizing a plurality of objects in a single object, recognition accuracy of the object can be improved.

Claims

1. A vehicle comprising:

a sensor input unit including a Light Detection and Ranging (LIDAR) device, said LIDAR device including a laser ray transmission unit to transmit a plurality of laser rays so as to scan a surrounding area of the vehicle; and

a laser ray reception unit to receive reflected laser rays from the surrounding area of the vehicle;

a coordinate specifying unit to specify coordinates of reflection points for said reflected laser rays;

a reliability setting unit to indicate an object presence reliability value of whether an object is present in the surrounding area of the vehicle, said object presence reliability value being one of a continuous range of values;

a distribution map creation unit to create a distribution map of the object presence reliability values in the surrounding area of the vehicle; and

a region division unit to divide the distribution map into at least one region, wherein each region is an area of said distribution map having continuous object presence reliability values that are equal to or greater than a predetermined threshold value.

2. The vehicle of claim 1, further comprising:

a grouping unit to group the coordinates of said reflection points based on object presence reliability in an area between said reflection points.

3. The vehicle of claim 2, wherein said grouping unit is to group the coordinates of said reflection points such that a group of reflection points is based on the distribution map.

4. The vehicle of claim 3, wherein said grouping unit is to group the coordinates of said reflection points such that a group of the coordinates meets a predetermined criteria where a point-to-point distance of adjacent reflection points is equal to or less than a predetermined distance.

5. The vehicle of claim 4, further comprising an object recognition unit to estimate a shape of an object corresponding to the group of coordinates from said grouping unit where the object presence reliability values are equal to or greater than a predetermined threshold value.

6. The vehicle of claim 5, wherein the object recognition unit is to recognize an object in the surrounding area of the vehicle based on the estimated shape of the object.

7. An object recognition device comprising:

a sensor input unit including a Light Detection and Ranging (LIDAR) device, said LIDAR device including a laser ray transmission unit to transmit a plurality of laser rays so as to scan a surrounding area of a vehicle; and

a laser ray reception unit to receive reflected laser rays from the surrounding area of the vehicle;

a coordinate specifying unit to specify coordinates of reflection points for said reflected laser rays;

a reliability setting unit to indicate an object presence reliability value of whether an object is present in the surrounding area of the vehicle, said object presence reliability value being one of a continuous range of values;

a distribution map creation unit to create a distribution map of the object presence reliability values in the surrounding area of the vehicle; and

a region division unit to divide the distribution map into at least one region, wherein each region is an area of said distribution map having continuous object presence reliability values that are equal to or greater than a predetermined threshold value.

8. The object recognition device of claim 7, further comprising:

a grouping unit to group the coordinates of said reflection points based on object presence reliability in an area between said reflection points.

9. The object recognition device of claim 8, wherein said grouping unit is to group the coordinates of said reflection points such that a group of reflection points is based on the distribution map.

10. The object recognition device of claim 9, wherein said grouping unit is to group the coordinates of said reflection points such that a group of the coordinates meets a predetermined criteria where a point-to-point distance of adjacent reflection points is equal to or less than a predetermined distance.

11. The object recognition device of claim 10, further comprising an object recognition unit to estimate a shape of an object corresponding to the group of coordinates from said grouping unit where the object presence reliability values are equal to or greater than a predetermined threshold value.

12. The object recognition device of claim 11, wherein the object recognition unit is to recognize an object in the surrounding area of the vehicle based on the estimated shape of the object.

13. A method of detecting an object in an area surrounding a vehicle comprising:

transmitting a plurality of laser rays from a Light Detection and Ranging (LIDAR) device of a sensor input unit so as to scan the surrounding area of the vehicle;

receiving reflected laser rays from the surrounding area of the vehicle;

specifying coordinates of reflection points for said reflected laser rays;

setting an object presence reliability value of whether an object is present in the surrounding area of the vehicle, said object presence reliability value being one of a continuous range of values;

creating a distribution map of the object presence reliability values in the surrounding area of the vehicle; and

dividing the distribution map into at least one region, wherein each region is an area of said distribution map having continuous object presence reliability values that are equal to or greater than a predetermined threshold value.

14. The method of claim 13, further comprising:

grouping the coordinates of said reflection points based on object presence reliability in an area between said reflection points.

15. The method of claim 14, wherein said grouping the coordinates of said reflection points is performed such that a group of reflection points is based on the distribution map.

16. The method of claim 15, wherein said grouping the coordinates of said reflection points is performed such that a group of the coordinates meets a predetermined criteria where a point-to-point distance of adjacent reflection points is equal to or less than a predetermined distance.

17. The method of claim 16, further comprising:

estimating a shape of an object corresponding to the group of coordinates from said grouping operation where the object presence reliability values are equal to or greater than a predetermined threshold value.

18. The method of claim 17, further comprising:

recognizing an object in the surrounding area of the vehicle based on the estimated shape of the object.