Apparatus and method for extracting feature point for recognizing obstacle using laser scanner

• US 9,958,260 B2
• Filed: 12/27/2013
• Issued: 05/01/2018
• Est. Priority Date: 09/25/2013
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Industry Academic Cooperation Foundation, Kia Motors Corporation (Kia Corp.)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group), Industry Academic Cooperation Foundation, Kia Motors Corporation (Kia Corp.)
• Inventors: Yoo, Minkyun, Kim, Hyunju, Lee, Hoon, Kim, Youngwon, Jang, Hyungsun, Choi, Baehoon, Kim, Beomseong, Kim, Euntai
• Primary Examiner(s): Gray, David M
• Assistant Examiner(s): Evans, Geoffrey T
• Application Number:
  US14/142,054
• Publication Number:
  US 20150088456A1
• Time in Patent Office: 1,586 Days
• CPC Class Codes: G01B 11/14 for measuring distance or clearance between spaced objects or spaced apertures G01B11/26 takes precedence; rangefinders G01C3/00
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• 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: G01S 7/4802 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• 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: 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 apparatus and method for extracting a feature point to recognize an obstacle using a laser scanner are provided. The apparatus includes a laser scanner that is installed at a front of a traveling vehicle and is configured to obtain laser scanner data having a plurality of layers in real time. In addition, a controller is configured to separate the laser scanner data obtained by the laser scanner into a plurality of layers to extract measurement data present in each layer and determine feature points of the measurement data to classify a type of obstacle based on a plurality of stored feature points.

Claims

1. An apparatus for extracting a feature to recognize an obstacle using a laser scanner, the apparatus comprising:

a laser scanner installed at a front of a traveling vehicle and configured to obtain laser scanner data having a plurality of layers in real time; and

a controller configured to separate the laser scanner data obtained by the laser scanner into a plurality of layers to extract measurement data present in each layer and determine features of the measurement data to classify a type of obstacle based on a plurality of stored features,

wherein the features comprise at least one of a form of the measurement data present in the layer, a number or position of measurement data present in each layer or whether the layer in which the measurement data is not present is present.

2. The apparatus according to claim 1, wherein the controller is configured to restore a three-dimensional coordinate value for the measurement data using layer information and calculate a standard deviation of a distance between the traveling vehicle and the obstacle using an average value derived from the coordinate value.

3. The apparatus according to claim 1, wherein the controller is configured to calculate a distance difference up to a virtual plane to minimize a distance from the coordinate values.

4. The apparatus according to claim 1, wherein the controller is configured to calculate a summation of an area of each layer in which the coordinate value is present.

5. The apparatus according to claim 1, wherein the controller is configured to calculate an average value for an area of each layer in which the coordinate value is present.

6. The apparatus according to claim 1, wherein the controller is configured to calculate a gradient of a line segment or a coefficient of a curve generated from the measurement data.

7. A method for extracting a feature to recognize an obstacle using a laser scanner, the method comprising:

obtaining, by a controller, laser scanner data having a plurality of layers in real time from the laser scanner installed at a front of a traveling vehicle;

separating, by the controller, the laser scanner data into a plurality of layers;

extracting, by the controller, measurement data present in each layer; and

determining, by the controller, features of the measurement data to classify a type of obstacle present at the front of the traveling vehicle based on a plurality of stored features,

wherein the features comprise at least one of a form of the measurement data present in the layer, a number or position of measurement data present in each layer or whether the layer in which the measurement data is not present is present.

8. The method according to claim 7, wherein the determination of the features of the measurement data includes:

restoring, by the controller, a three-dimensional coordinate value for the measurement data using layer information; and

calculating, by the controller, a standard deviation of a distance between the traveling vehicle and the obstacle using an average value derived from the coordinate value.

9. The method according to claim 7, wherein the determination of the features of the measurement data includes:

calculating, by the controller, a distance difference up to a virtual plane to minimize a distance from the coordinate values.

10. The method according to claim 7, wherein the determination of the features of the measurement data includes:

calculating, by the controller, a summation of an area of each layer in which the coordinate value is present.

11. The method according to claim 7, wherein the determination of the features of the measurement data includes:

calculating, by the controller, an average value for an area of each layer in which the coordinate value is present.

12. The method according to claim 7, wherein the determination of the features of the measurement data includes:

calculating, by the controller, a gradient of a line segment or a coefficient of a curve generated from the measurement data.

13. A non-transitory computer readable medium containing program instructions executed by a controller, the computer readable medium comprising:

program instructions that obtain laser scanner data having a plurality of layers in real time from a laser scanner installed at a front of a traveling vehicle;

program instructions that separate the laser scanner data into a plurality of layers;

program instructions that extract measurement data present in each layer; and

program instructions that determine features of the measurement data to classify a type of obstacle present at the front of the traveling vehicle based on a plurality of stored features,

wherein the features comprise at least one of a form of the measurement data present in the layer, a number or position of measurement data present in each layer or whether the layer in which the measurement data is not present is present.

14. The non-transitory computer readable medium of claim 13 further comprising:

program instructions that restore a three-dimensional coordinate value for the measurement data using layer information and calculate a standard deviation of a distance between the traveling vehicle and the obstacle using an average value derived from the coordinate value.