Object detecting apparatus, and method of operating the same

• US 9,435,887 B2
• Filed: 04/27/2015
• Issued: 09/06/2016
• Est. Priority Date: 10/23/2014
• Status: Active Grant

• Current Assignee: Hyundai Mobis Co., Ltd.
• Original Assignee: Hyundai Mobis Co., Ltd.
• Inventors: Kim, Young shin, Ryu, Soo yong, Kim, Won gyum
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): Lee, Tyler J
• Application Number:
  US14/697,097
• Publication Number:
  US 20160116593A1
• Time in Patent Office: 498 Days
• Field of Search: 701/36, 701/70, 701300-301
• US Class Current: 1/1
• CPC Class Codes: B60T 2201/022 Collision avoidance systems
• CPC Class Codes: B60T 2210/32 Vehicle surroundings
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: G01P 3/36 Devices characterised by the use of optical means, e.g. using infrared, visible, or ultraviolet light G01P3/68 takes precedence; gyrometers using the Sagnac effect, i.e. rotation-induced shifts between counter-rotating electromagnetic beams G01C19/64
• CPC Class Codes: G01S 17/06 Systems determining position data of a target
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30261 Obstacle
• 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

Abstract

An object detecting apparatus and an operating method thereof are disclosed. An apparatus for detecting an object includes: a sensor unit including a light distance and ranging (LiDAR) sensor for collecting LiDAR data and a camera sensor for collecting image data; an area dividing unit configured to divide a common detection area of the LiDAR sensor and the camera sensor into a plurality of areas; a data analyzing unit configured to analyze the LiDAR data to extract a first object information and/or analyze the image data to extract a second object information; and a sensor signal converging unit configured to determine whether a dangerous object exists for each of the divided areas based on the first object information and/or the second object information.

Claims

1. An apparatus for detecting an object, comprising:

a sensor unit including a light distance and ranging (LiDAR) sensor configured for collecting LiDAR data and a camera sensor configured for collecting image data;

an area dividing unit configured to divide a common detection area of the LiDAR sensor and the camera sensor into a plurality of areas;

a data analyzing unit configured to analyze the LiDAR data to extract a first object information and analyze the image data to extract a second object information;

a sensor signal converging unit configured to determine whether a dangerous object exists for each of the divided areas based on the first object information and the second object information; and

a vehicle information collecting unit configured to collect speed information about a vehicle,

wherein;

the plurality of areas divided by the area dividing unit comprise a ground non-included area and a ground included area;

the data analyzing unit is configured to insert relative speed information of an object against the vehicle into at least one of the first object information and the second information; and

the sensor signal converging unit is configured to determine that a dangerous object exists in the ground included-area when the first object information about the ground included is about a stopped object and the second object information about the stopped object is included in the image data.

2. The apparatus of claim 1, wherein the sensor signal converging unit comprises:

a coordinate converging module configured to convert the LiDAR data and the image data into data in a coordinate plane; and

an object comparing module configured to compare the first object information included in the LiDAR data and the second object information included in the image data in the coordinate plane,

wherein the sensing signal converging unit is configured to determine whether a dangerous objects exists for each of the divided areas based on a result of the comparison.

3. The apparatus of claim 2, wherein when the first object information and the second object information have a difference less than a predetermined threshold value as a result of the comparison, the sensor signal converging unit is configured to determine that a first object and a second object are the same object.

4. The apparatus of claim 2, wherein:

the first object information is center coordinates of a first object for the coordinate plane; and

the second object information is center coordinates of a second object for the coordinate plane.

5. The apparatus of claim 1, wherein when the data analyzing unit extracts the first object information from the LiDAR data for the ground non-included area, the sensor signal converging unit is configured to determine that a dangerous object exists in the ground non-included area.

6. The apparatus of claim 1, wherein the sensor unit is configured to adjust an object detection threshold value of the camera sensor based on a predetermined sensitivity adjustment condition.

7. The apparatus of claim 1, wherein:

the data analyzing unit is configured to insert relative speed information of an object against the vehicle into at least one of the first object information and the second object information; and

the sensor signal converging unit is configured to determine whether the first object information about the ground included area is related to a stopped object based on the relative speed information, and when it is determined that the first object information is related to the moving object, the sensor signal converging unit is configured to determine that a dangerous object exists in the ground included area.

8. The apparatus of claim 1, further comprising a driving unit configured to operate an autonomous emergency braking (AEB) system of the vehicle when the sensor signal converging unit processes that the dangerous object exists.

9. The apparatus of claim 1, further comprising a synchronizing unit configured to synchronize the LiDAR data transmitted from the LiDAR sensor and the image data transmitted from the camera sensor based on a time,

wherein the sensor signal converging unit is configured to determine whether a dangerous object exists for each of the divided areas based on the first object information and the second object information when the synchronization is completed.

10. An apparatus for detecting an object, comprising:

a sensor unit comprising a light distance and ranging (LiDAR) sensor configured for collecting LiDAR data and a camera sensor configured for collecting image data;

an area dividing unit configured to divide a common detection area of the LiDAR sensor and the camera sensor into a plurality of areas;

a data analyzing unit configured to analyze the LiDAR data to extract a first object information and analyze the image data to extract a second object information;

a sensor signal converging unit configured to determine whether a dangerous object exists for each of the divided areas based on the first object information and the second object information; and

a vehicle information collecting unit configured to collect speed information about a vehicle,

wherein;

the plurality of areas divided by the area dividing unit comprise a ground non-included area and a ground included area;

the data analyzing unit is configured to insert relative speed information of an object against the vehicle into at least one of the first object information and the second object information;

the sensor signal converging unit is configured to determine whether the first object information about the ground included area is related to a stopped object based on the relative speed information, and when it is determined that the first object information is related to the moving object, the sensor signal converging unit is configured to determine that a dangerous object exists in the ground included area;

the data analyzing unit is configured to extract lane path and boundary information included in the image data; and

when the first object information for the ground included area is related to a stopped object existing out of the lane boundary and in the lane path, the sensor signal converging unit determines that a dangerous object exists in the ground included area.

11. A method of operating an apparatus for detecting an object, comprising:

generating light distance and ranging LiDAR data by using a LiDAR sensor;

generating image data by using a camera sensor;

dividing a common detection area of the LiDAR sensor and the camera sensor into a ground non-included area and a ground included area;

analyzing at least one of the LiDAR data to extract first object information and the image data to extract second object information;

determining whether a dangerous object exists for each of the ground non-included area and the ground included area based on a result of the analysis;

operating an autonomous emergency braking (AEB) system of a vehicle when it is determined that the dangerous object exists; and

collecting speed information about a vehicle,

wherein the determining comprises determining whether the first object information included in the LiDAR data for the ground included area is related to a stopped object based on the speed information about the vehicle, and determining that a dangerous object exists in the ground included area when the first object information is related to a moving object.

12. The method of claim 11, wherein the step of determining comprises determining that a dangerous object exists in the ground non-included area when the first object information is included in the LiDAR data for the ground non-included area.

13. The method of claim 11, wherein the step of determining comprises determining that a dangerous object exists in the ground included area when an object related to the first object information and an object related to the second object information are the same based on the first information of the LiDAR data and the second object information of the image data.

14. The method of claim 11, further comprising adjusting an object detection threshold value of the camera sensor based on a predetermined sensitivity adjustment condition.

15. The method of claim 11, wherein:

the analyzing comprises extracting lane boundary information included in the image data; and

the determining comprises determining that a dangerous object exists in the ground included area when the first object information included in the LiDAR data for the ground included area is a stopped object existing out of a lane boundary.

16. A method of operating an apparatus for detecting an object, comprising:

generating light distance and ranging LiDAR data by using a LiDAR sensor;

generating image data by using a camera sensor;

dividing a common detection area of the LiDAR sensor and the camera sensor into a ground non-included area and a ground included area;

analyzing at least one of the LiDAR data to extract first object information and the image data to extract second object information;

determining whether a dangerous object exists for each of the ground non-included area and the ground included area based on a result of the analysis;

operating an autonomous emergency braking (AEB) system of a vehicle when it is determined that the dangerous object exists; and

collecting speed information about a vehicle,

wherein the step of determining comprises determining that a dangerous object exists in the ground included area when the first object information about the ground included area is about a stopped object and the second object information about the stopped object is included in the image data.