Object recognition system for vehicle

• US 7,468,791 B2
• Filed: 04/06/2005
• Issued: 12/23/2008
• Est. Priority Date: 04/09/2004
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Samukawa, Yoshie, Natsume, Tsutomu, Okuda, Keiko
• Primary Examiner(s): Tarcza; Thomas H.
• Assistant Examiner(s): Brainard; Timothy A
• Application Number:
  US11/099,974
• Publication Number:
  US 20050225744A1
• Time in Patent Office: 1,357 Days
• Field of Search: 356/28, 356/4.01, 356/325, 701/96, 701/300, 342/70, 342/71
• US Class Current: 356/325
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: G01S 17/14 wherein a voltage or current pulse is initiated and terminated in accordance with the pulse transmission and echo reception respectively, e.g. using counters
• 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 2007/4975 of sensor obstruction by, e.g. dirt- or ice-coating, e.g. by reflection measurement on front-screen
• 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 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• 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

An object recognition device for a vehicle includes a size determining means, an existence condition determining means, and an adverse condition determining means. The size determining means determines that the recognized objects are large when a size of the objects is larger than a given determination value. The existence condition determining means determines whether at least a given number of the objects are determined to be large by the size determining means. The adverse condition determining means identifies an adverse condition related to recognizing the objects when at least the given number of the objects are determined to be large by the existence condition determining means.

Claims

1. An object recognition device for a vehicle that irradiates transmitting waves away from a subject vehicle, acquires data corresponding to objects around the subject vehicle on the basis of reflected waves of the transmitting waves, and recognizes the objects on the basis of the data, the object recognition device comprising:

size determining means for determining a size of each of the recognized objects and that each of the recognized objects is large when at least a width of the recognized object is larger than a given determination value such that there is a high possibility that the recognized object does not exist;

existence condition determining means for determining whether at least a given number of the objects greater than two are determined to be large by the size determining means;

adverse condition determining means for identifying an adverse condition under which the objects cannot be normally detected when the given number of the objects are determined to be large by the existence condition determining means; and

control means for stopping vehicle travel control which uses the data acquired on the basis of the reflected waves when the adverse condition is identified.

2. The object recognition device according to claim 1, wherein at least the given number of the objects that are determined to be large objects exist in an object group including the recognized plurality of objects.

3. The object recognition device according to claim 2, wherein a plurality of determinations of the object group are implemented and the determinations are identified as adverse on the basis of the plurality of determination results.

4. The object recognition device according to claim 1, wherein it is determined that at least the given number of the large objects exist by the existence condition determining means.

5. The object recognition device according to claim 4, wherein a counter value used for determining the adverse conditions is changed according to the number of the objects that are determined as the large objects.

6. The object recognition device according to claim 5, wherein a variable value that changes the counter value is set for each of the object groups.

7. The object recognition device according to claim 5, wherein in a case where a velocity of the subject vehicle is lower than a given determination value, the counter value is set to 0.

8. The object recognition device according to claim 5, wherein in the case where a state in which the counter value is 0 continues for a given period of time after the determination of the adverse conditions is established, the determination of the adverse conditions is canceled.

9. The object recognition device according to claim 1, wherein a determination is made taking the operation of a wiper into consideration when it is determined that the conditions are adverse.

10. The object recognition device according to claim 1, wherein it is determined that the recognized object is large when all of the following conditions are satisfied:

a distance to the recognized object is within a given range;

a lateral position of the recognized object is within a given range;

the width of the recognized object is larger than the given determination value; and

a velocity of the subject vehicle is at least equal to a given value.

11. The object recognition device according to claim 10, wherein in the case where any one of the conditions is not satisfied, it is determined that the object is not large.

12. The object recognition device according to claim 1, wherein it is determined that the recognized object is large when all of the following conditions are satisfied:

a distance to the recognized object is within a given range;

a lateral position of the recognized object is within a given range;

the width of the recognized object is larger than the determination value;

a depth of the subject vehicle is at least equal to a given value; and

a velocity of the subject vehicle is at least equal to a given value.

13. The object recognition device according to claim 12, wherein in the case where any one of the conditions is not satisfied, it is determined that the object is not large.

14. The object recognition device according to claim 1, further comprising means for determining a distance to the objects.

15. The object recognition device according to claim 1, wherein the size determining means determines the size of the object based upon at least one of a lateral width and a depth of the object.

16. The object recognition device according to claim 1, wherein the size of the object is a two dimensional size of the object.

17. An object recognition device for a vehicle that irradiates transmitting waves away from a subject vehicle, acquires data corresponding to objects around the subject vehicle on the basis of reflected waves of the transmitting waves, and recognizes the objects on the basis of the data, the object recognition device comprising:

size determining means for determining a size of each of the recognized objects and that each of the recognized objects is large when the size of the recognized object is larger than a given determination value such that there is a high possibility that the recognized object does not exist;

existence condition determining means for determining whether at least a given number of the objects greater than two are determined to be large by the size determining means; and

adverse condition determining means for identifying an adverse condition under which the objects cannot be normally detected when the given number of the objects are determined to be large by the existence condition determining means;

wherein

a determination is made taking the operation of a wiper into consideration when it is determined that the conditions are adverse.

18. An object recognition device for a vehicle that irradiates transmitting waves away from a subject vehicle, acquires data corresponding to objects around the subject vehicle on the basis of reflected waves of the transmitting waves, and recognizes the objects on the basis of the data, the object recognition device comprising:

size determining means for determining a size of each of the recognized objects based on a width and a depth of each of the recognized objects and that each of the recognized objects is large when the size of the recognized object is larger than a given determination value such that there is a high possibility that the recognized object does not exist;

existence condition determining means for determining whether at least a given number of the objects greater than two are determined to be large by the size determining means; and

adverse condition determining means for identifying an adverse condition under which the objects cannot be normally detected when the given number of the objects are determined to be large by the existence condition determining means.

19. The object recognition device according to claim 18, wherein at least the given number of the objects that are determined to be large objects exist in an object group including the recognized plurality of objects.

20. The object recognition device according to claim 18, wherein it is determined that at least the given number of the large objects exist by the existence condition determining means.

21. The object recognition device according to claim 18, wherein a determination is made taking the operation of a wiper into consideration when it is determined that the conditions are adverse.

22. The object recognition device according to claim 18, wherein it is determined that the object is large when all of the following conditions are satisfied:

a distance to the object is within a given range (condition A);

a lateral position of the object is within a given range (condition B);

a lateral width of the object is at least equal to a given threshold value (condition C);

the lateral width of the object is at least equal to a given threshold value (condition D), wherein the threshold value C<

the threshold value D; and

a velocity of the subject vehicle is at least equal to a given value (condition F).

23. The object recognition device according to claim 18, wherein it is determined that the object is large when all of the following conditions are satisfied:

a distance to the object is within a given range (condition A);

a lateral position of the object is within a given range (condition B);

a lateral width of the object is at least equal to a given threshold value (condition C);

a depth of the subject vehicle is at least equal to a given value (condition E); and

a velocity of the subject vehicle is at least equal to a given value (condition F).

24. An object recognition device for a vehicle that irradiates transmitting waves away from a subject vehicle, acquires data corresponding to objects around the subject vehicle on the basis of reflected waves of the transmitting waves, and recognizes the objects on the basis of the data, the object recognition device comprising:

means for determining a high possibility that each of the recognized objects does not exist when a width of the recognized object is larger than a given value;

means for determining whether a specified number of the objects greater than two are determined to have the high possibility to not exist;

means for identifying an adverse condition under which the objects cannot be normally detected when the specified number of the objects are determined to have the high possibility to not exist; and

means for stopping vehicle travel control which uses the data acquired on the basis of the reflected waves when the adverse condition is identified.