Object classification adjustment based on vehicle communication

• US 10,528,850 B2
• Filed: 11/02/2016
• Issued: 01/07/2020
• Est. Priority Date: 11/02/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Surnilla, Gopichandra, Smith, Stephen B., Makled, Daniel A., Mcquillen, Michael
• Primary Examiner(s): Yentrapati, Avinash
• Application Number:
  US15/341,050
• Publication Number:
  US 20180121763A1
• Time in Patent Office: 1,161 Days
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• 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 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• 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 1/163 involving continuous checking
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

Method, apparatus and computer readable media are disclosed for object classification adjustment based on vehicle communication. An example vehicle includes a camera to detect an object and an object classifier. The example object classifier is to determine first classification data for the object. The first classification data includes a classification confidence of the object. Also, the example object classifier is to associate second classification data for the object with the first classification data. The second classification data is collected from a second vehicle. Additionally, the example object classifier is to adjust the classification confidence of the object based on the second classification data.

Claims

1. A method comprising:

detecting an object via a camera of a first vehicle;

determining, via a processor of the first vehicle, first classification data that includes a first classification confidence and a location for the object;

broadcasting the first classification data from the first vehicle to enable a second vehicle to identify second classification data that includes a second classification confidence for the object;

determining, via a second processor of the second vehicle, that the first classification data and the second classification data includes the location;

collecting the second classification data at the first vehicle from the second vehicle;

determining, via the processor of the first vehicle, a reliability score for the second vehicle; and

adjusting the first classification confidence for the object based on the second classification data and the reliability score of the second vehicle.

2. The method of claim 1, further including broadcasting the first classification confidence of the object to the second vehicle after adjusting the first classification confidence based on the second classification data of the second vehicle.

3. The method of claim 1, further including at least one of emitting a warning to a driver and performing an autonomous motive function based upon the first classification data of the object.

4. A vehicle comprising:

a camera for detecting an object;

a communication module; and

a controller configured to;

determine first classification data for the object, the first classification data including a first classification confidence and a location;

broadcast, via the communication module, the first classification data to enable a second vehicle to identify second classification data of the object;

collect, via the communication module, the second classification data that includes a second classification confidence and the location from the second vehicle;

in response to determining that the first classification data and the second classification data includes the location, associate the second classification data with the first classification data;

adjust the first classification confidence of the object based on the second classification data; and

determine a reliability score for the second vehicle and adjust the first classification confidence of the object further based on the reliability score of the second vehicle.

5. The vehicle of claim 4, further including a radar sensor that collects location data of the object to enable the controller to determine a location of the object.

6. The vehicle of claim 4, wherein the controller further adjusts at least one of the first classification data and the first classification confidence based on third classification data collected from at least one of a roadside unit and a mobile device.

7. The vehicle of claim 4, wherein the first classification data of the object is selected from the group consisting of a car, a motorcycle, an SUV, a pickup truck, a semi-truck, a van, a bus, a bicycle, a pedestrian, and an animal.

8. The vehicle of claim 4, wherein the controller is configured to:

reduce the reliability score upon determining that data collected by the second vehicle is less reliable; and

increase the reliability score upon determining that the data collected by the second vehicle is more reliable.

9. The vehicle of claim 4, wherein the controller is configured to adjust the first classification data based on the second classification confidence and the reliability score of the second vehicle, the controller weights the second classification confidence with the reliability score.

10. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on historical data of the second vehicle.

11. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on:

a type of sensor of the second vehicle that detected the object; and

a distance between the second vehicle and the detected object.

12. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on an environmental condition when a sensor of the second vehicle detected the object.

13. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on at least one of an age and a mileage of the second vehicle.

14. The vehicle of claim 4, wherein, to adjust the first classification configured based on the second classification confidence and the reliability score of the second vehicle, the controller weights the second classification confidence with the reliability score.

15. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on historical data of the second vehicle.

16. The vehicle of claim 4, wherein the controller determines the reliability score of the second vehicle based on:

a type of sensor of the second vehicle that detected the object; and

a distance between the second vehicle and the detected object.

17. The vehicle of claim 4, wherein the communications module is a dedicated short-range communications module.