Device and method for recognizing obstacle and parking slot to support unmanned autonomous parking function

Patent metadata

Field	Value
Publication number	US-10025997-B2
Application number	US-201615130907-A
Country	US
Kind code	B2
Filing date	Apr 15, 2016
Priority date	Apr 16, 2015
Publication date	Jul 17, 2018
Grant date	Jul 17, 2018

Abstract

Provided herein is a device and a method for recognizing an obstacle and a parking slot to support an unmanned autonomous parking function. The device includes a motion measurement unit measuring a vehicle motion using an in-vehicle sensor, an inverse perspective transform unit performing inverse perspective transformation of an image, which is obtained using a wide-angle camera, to obtain an inverse perspective image, and an obstacle detection unit detecting the obstacle using the inverse perspective image.

First claim

What is claimed is:

1. A device for recognizing an obstacle and a parking slot to support an unmanned autonomous parking function, the device comprising:
a processor, and
a non-transitory medium having program instructions stored thereon, execution of which causes the processor to provide functions of
a motion measurement unit configured to measure a vehicle motion using an in-vehicle sensor;
an inverse perspective transform unit configured to perform inverse perspective transformation of an image obtained by a camera, and obtain an inverse perspective image; and
an obstacle detection unit configured to detect the obstacle using the inverse perspective image, by
obtaining an image before and after the vehicle motion and performing stereo rectification of the image using a SFM (structure from motion) technology,
performing dense reconstruction from the rectified image, and
projecting the image that is subjected to the dense reconstruction on a two-dimensional grid map, and segmenting the image according to a height and detecting the obstacle, such that

the detected obstacle is used for unmanned autonomous parking, and
motion stereo is directly performed using the inverse perspective image to provide depth information without any coordinate transformation.

2. The device according to claim 1 , wherein the execution of the program instructions causes the processor to further provide functions of:
a line marking detection unit configured to detect a parking slot marking line using the inverse perspective image.

3. The device according to claim 2 , wherein the execution of the program instructions causes the processor to further provide functions of:
a map building unit configured to build a line marking map using information transferred from the obstacle detection unit and the line marking detection unit.

4. The device according to claim 3 , wherein the execution of the program instructions causes the processor to further provide functions of:
a parking space recognition unit configured to recognize a parking space using the line marking map built by the map building unit.

5. The device according to claim 1 , wherein the in-vehicle sensor includes at least one of a wheel speed sensor, a yaw rate sensor, and a steering angle sensor.

6. A method of recognizing an obstacle and a parking slot to support an unmanned autonomous parking function, the method comprising:
measuring a vehicle motion using an in-vehicle sensor;
performing inverse perspective transformation of an image obtained by a camera, and obtaining an inverse perspective image;
detecting the obstacle using the inverse perspective image, including
obtaining an image before and after the vehicle motion and performing stereo rectification of the image using a SFM (structure from motion) technology,
performing dense reconstruction from the rectified image, and
projecting the image that is subjected to the dense reconstruction on a two-dimensional grid map, and segmenting the image according to a height and detecting the obstacle; and

detecting a parking slot marking line using the inverse perspective image, such that
the detected obstacle is used for unmanned autonomous parking, and
motion stereo is directly performed using the inverse perspective image to provide depth information without any coordinate transformation.

7. The method according to claim 6 , further comprising:
building a line marking map using detected obstacle information and parking slot marking line information.

8. The method according to claim 7 , further comprising:
recognizing a parking space using the line marking map.

9. The method according to claim 6 , wherein the in-vehicle sensor includes at least one of a wheel speed sensor, a yaw rate sensor, and a steering angle sensor.

Assignees

• Electronics & Telecommunications Res Inst

Inventors

• Han Seung Jun
• Min Kyoung Wook
• Park Sang Heon
• Sung Kyung Bok
• Choi Jeong Dan

Classifications

• B62D15/0285 Primary

  Parking performed automatically · CPC title

• G06K9/00805

  Physics · mapped topic

• G06K9/00798 Primary

  Physics · mapped topic

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title