System and method for automatic trailer detection

• US 10,488,504 B2
• Filed: 01/19/2017
• Issued: 11/26/2019
• Est. Priority Date: 01/19/2017
• Status: Active Grant

• Current Assignee: Arriver Software LLC
• Original Assignee: Veoneer US Inc. (SSW Partners LP)
• Inventors: Di, Junru, Cong, Shan, Gupta, Kapil, Sivako, Malakeh, Rice, Debra, Attard, Joe
• Primary Examiner(s): Barker, Matthew M
• Application Number:
  US15/410,621
• Publication Number:
  US 20180203106A1
• Time in Patent Office: 1,041 Days
• CPC Class Codes: G01S 13/04 Systems determining presence of a target based on relative movement of target G01S13/56
• CPC Class Codes: G01S 13/87 Combinations of radar systems, e.g. primary radar and secondary radar
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 2013/93272 in the back of the vehicles
• CPC Class Codes: G01S 7/2922 by using a controlled threshold
• CPC Class Codes: G01S 7/411 Identification of targets based on measurements of radar reflectivity G01S7/415 takes precedence
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees

Abstract

A system and method for determining when a trailer is located behind a vehicle includes at least one detection device configured to detect objects located behind the vehicle and a processor. The processor is in communication with the at least one detection device and a plurality of signals generated by the vehicle. The processor receives data from the at least one detection device. The data includes a plurality of targets detected by the at least one detection device. Next, the processor determines if one or more clusters exists and clusters the targets into at least one cluster to form cluster features when one or more clusters exist. The processor determines vehicle state based on the vehicle dynamic features from the plurality of signals generated by the vehicle as well as global features from data from the at least one detection device and determines when the trailer is located behind the vehicle based on the cluster features, the vehicle state, and/or the global features.

Claims

1. A system for determining when a trailer is located behind a vehicle, the system comprising:

at least one detection device configured to detect objects located behind the vehicle;

a processor, the processor being in communication with the at least one detection device and a plurality of signals generated by the vehicle;

the processor being configured to;

receive data from the at least one detection device, the data including a plurality of targets detected by the at least one detection device,

identify if at least one cluster exists and cluster the targets into at least one cluster to form cluster features when at least one cluster exists,

determine a vehicle state based on vehicle dynamic features from the plurality of signals generated by the vehicle, wherein vehicle state includes at least one of the following;

stopped, turning, traveling straight at a steady speed, or traveling straight under acceleration,

determine global features from data from the at least one detection device, the global features include statistical features, spatial features and relative velocity features, statistical features include at least one of the following;

standard deviation of the targets in either the X or Y direction or the standard deviation of the difference of the targets in either the X or Y direction, the largest difference in the Y direction or principle component analysis of the targets, spatial features include quantized spatial data in the X direction or Y direction, relative velocity features include ratio of data in different relative speed bins; and

determine when the trailer is located behind the vehicle based on the vehicle state and at least one of the cluster features or the global features.

2. The system of claim 1, wherein the at least one detection device is a radar device.

3. The system of claim 1, wherein the processor is configured to identify the location of detected targets or cluster the targets utilizing either hierarchical clustering, centroid-based clustering (k-mean), distribution-based clustering (Gaussian mixture models) or density-based clustering.

4. The system of claim 3 wherein processor is configured to use density based clustering and when using density-based clustering, the at least one cluster only includes targets that are a specified distance from each other and the total number of targets within a cluster exceeds a threshold value.

5. The system of claim 1, wherein the processor is further configured to determine when the trailer is located behind the vehicle by setting a threshold for the global features and the cluster features, wherein exceeding the threshold is indicative that the trailer is located behind the vehicle.

6. The system of claim 1, wherein the processor is further configured to determine when the trailer is located behind the vehicle by weighing the cluster features or the global features based on the state of the vehicle.

7. The system of claim 1, wherein the processor is further configured to pre-process the data before clustering occurs.

8. The system of claim 7, wherein the pre-process includes filtering the data to remove targets outside a region of interest.

9. The system of claim 7, wherein the pre-process includes filtering the data to remove targets that have a relative speed higher than a certain value.

10. The system of claim 1, wherein the spatial features include a brightest spot shift, ratio of data points in brightest spot in data size, ratio of number of darkest spots and data size, or rank of spatial frequency matrix.

11. A method for determining when a trailer is located behind a vehicle, the method comprising:

receiving data from at least one detection device configured to detect objects located behind the vehicle, the data including a plurality of targets detected by the at least one detection device;

identifying if at least one cluster exists and clustering the targets into at least one cluster to form cluster features when at least one cluster exists;

determining a vehicle state based on dynamic features from a plurality of signals generated by the vehicle, wherein the vehicle state includes at least one of the following;

stopped, turning, traveling straight at a steady speed, or traveling straight under acceleration;

determining global features from data from the at least one detection device, the global features include statistical features, spatial features, and relative velocity features, statistical features include at least one of the following;

statistical features of the standard deviation of the targets in either the X or Y direction or the standard deviation of the difference of the targets in either the X or Y direction, the largest difference in the Y direction or principle component analysis of the targets, spatial features include quantized spatial data in the x-direction or y-direction, relative velocity features include ratio of data in different relative speed bins; and

determining when the trailer is located behind the vehicle based on the vehicle state and at least one of the cluster features or the global features.

12. The method of claim 11, wherein the at least one detection device is a radar device.

13. The method of claim 11, further comprising identifying the location of detected targets or clustering the targets utilizing either hierarchical clustering, centroid-based clustering (k-mean), distribution-based clustering (Gaussian mixture models) or density-based clustering.

14. The method of claim 13 wherein the location of targets or clustering of targets is identified using density-based clustering, and the at least one cluster only includes targets that are a specified distance from each other and the total number of targets within a cluster exceeds a threshold value.

15. The method of claim 11, further comprising determining when the trailer is located behind the vehicle by setting a threshold for the global features and the cluster features, wherein exceeding the threshold is indicative that the trailer is located behind the vehicle.

16. The method of claim 11, further comprising determining when the trailer is located behind the vehicle by weighing the cluster features or the global features based on the state of the vehicle.

17. The method of claim 11, further comprising pre-processing the data before the step of clustering occurs.

18. The method of claim 17, wherein the step of pre-processing includes filtering the data to remove targets outside a region of interest.

19. The method of claim 17, wherein the step of pre-processing includes filtering the data to remove targets that have a relative speed higher than a certain value.

20. The method of claim 11, wherein the spatial features include a brightest spot shift, ratio of data points in brightest spot in data size, ratio of number of darkest spots and data size, or rank of spatial frequency matrix.