Method for classifying an object as an obstacle

• US 8,731,816 B2
• Filed: 01/14/2010
• Issued: 05/20/2014
• Est. Priority Date: 04/22/2009
• Status: Active Grant

• Current Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Original Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Inventors: Dintzer, Philippe, Stephan, Tobias, Randler, Martin, Hanel, Nele
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): OH, HARRY Y
• Application Number:
  US13/258,694
• Publication Number:
  US 20120130628A1
• Time in Patent Office: 1,587 Days
• Field of Search: 701/301
• US Class Current: 701/301
• CPC Class Codes: G01S 13/52 Discriminating between fixed and moving objects or between objects moving at different speeds
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/931 of land vehicles
• 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 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A method for classifying objects into obstacles and non-obstacles for a vehicle is described. The vehicle comprises a sensor for covering the surroundings that detects stationary and moving objects in a scene in front of a vehicle. Where required, the path of the motion of the objects is tracked. The method provides one or several observers, wherein one observer classifies an object according to predetermined features and contributes to an overall classification result when there are several observers. An observer detects the path of the motion of vehicles in the surroundings of at least one stationary object and classifies the stationary object in dependence thereon.

Claims

1. A method of classifying an object as an obstacle for a subject vehicle with a sensor for monitoring a surrounding environment of the subject vehicle, comprising

using the sensor, detecting stationary objects and moving objects in a scene in the surrounding environment in front of the subject vehicle, and when required tracking a respective path of motion of at least one of the moving objects, and

using an observer arrangement that includes at least one observer, detecting a path of motion of at least one other vehicle approaching a first one of the stationary objects in the surrounding environment, and classifying the first one of the stationary objects as an obstacle or a non-obstacle for the subject vehicle dependent on the path of motion of the other vehicle.

2. The method according to claim 1, further comprising

using the sensor, determining roadside border lines, and

using the observer arrangement, classifying at least one of the stationary objects as an obstacle or a non-obstacle dependent on a shape of the respective stationary object, wherein particularly if the respective stationary object is a coherent object extending laterally beyond the roadside border lines then the respective stationary object is classified as a potential bridge and thus as a non-obstacle.

3. The method according to claim 1, further comprising,

using the observer arrangement, classifying at least one of the stationary objects as a non-obstacle if the respective stationary object has a significantly smaller dispersion or extension than a typical obstacle, particularly a vehicle.

4. The method according to claim 1, further comprising,

using the sensor, determining roadside border lines,

using the observer arrangement, classifying at least one of the stationary objects as a non-obstacle if the respective stationary object is located along one of the roadside border lines and is recognized as a roadway boundary object, and

using the observer arrangement, classifying as obstacles only respective ones of the objects that are located on a roadway between the roadside border lines.

5. The method according to claim 1, further comprising

determining a distribution of a mean maximum confirmation density of the objects relative to a longitudinal distance of the objects from the sensor, and

classifying at least one of the objects as an obstacle or as a non-obstacle dependent on the distribution of the mean maximum confirmation density of the respective object.

6. A method comprising the steps:

a) using a sensor arrangement including at least one sensor on a subject vehicle, detecting an object and a moving vehicle in an environment outside of said subject vehicle, and producing sensor data indicative of said object and said moving vehicle;

b) in an evaluation arrangement on said subject vehicle, evaluating said sensor data and thereby monitoring a motion characteristic of said moving vehicle in relation to at least one of a position and a path of said object, wherein said motion characteristic includes at least one of a motion path and a velocity progression of a motion of said moving vehicle; and

c) in said evaluation arrangement, classifying said object as an obstacle or a non-obstacle for the subject vehicle in response to and dependent on said motion characteristic of said moving vehicle.

7. The method according to claim 6, further comprising providing from said evaluation arrangement to a driver assistance system on said subject vehicle, information regarding whether said object was classified as said obstacle or as said non-obstacle, and adjusting an operation of said driver assistance system in response to and dependent on said information.

8. The method according to claim 6, wherein said object is a stationary object and said motion characteristic of said moving vehicle is monitored in relation to said position of said stationary object.

9. The method according to claim 6, wherein said object is a moving object and said motion characteristic of said moving vehicle is monitored in relation to said path of said moving object.

10. The method according to claim 6, wherein, if said evaluating and said monitoring in said step b) determine that said moving vehicle passes over or under said object, then said classifying in said step c) classifies said object as said non-obstacle.

11. The method according to claim 6, wherein, if said evaluating and said monitoring in said step b) determine that said motion path of said moving vehicle swerves around said position or said path of said object, or that said velocity progression of said moving vehicle slows down so that said moving vehicle avoids said position or said path of said object, then said classifying in said step c) classifies said object as said obstacle.