Method for performing diagnosis of a camera system of a motor vehicle, camera system and motor vehicle

• US 10,178,382 B2
• Filed: 04/28/2015
• Issued: 01/08/2019
• Est. Priority Date: 05/08/2014
• Status: Active Grant

• Current Assignee: Valeo Schalter und Sensoren GmbH (Valeo SE)
• Original Assignee: Valeo Schalter und Sensoren GmbH (Valeo SE)
• Inventors: Chanussot, Lowik, Rebut, Julien
• Primary Examiner(s): Williams, Jeffery A
• Application Number:
  US15/308,709
• Publication Number:
  US 20170180723A1
• Time in Patent Office: 1,351 Days
• Field of Search: 348148
• CPC Class Codes: B60T 8/171 Detecting parameters used in the regulation; Measuring values used in the regulation
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 10/98 Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

The invention relates to a method for performing a diagnosis of a camera system (2) of a motor vehicle (1) by: providing at least one image (BD) by means of a camera (3); detecting an object (6) in the image (BD) by means of an image processing device; providing sensor data (SD) by means of at least one sensor (7) of the motor vehicle (1), wherein the sensor data (SD) characterizes environmental conditions of the motor vehicle (1); first classifying the object (6) and herein associating the object (6) with a class (K1, K2, K3, K4) among several predetermined classes (K1, K2, K3, K4) depending on the environmental conditions, wherein the classes (K1, K2, K3, K4) differ from each other with respect to the environmental conditions; second classifying the at least one object (6) and herein associating the object (6) with one of the classes (K1, K2, K3, K4) based on the image (BD) and independently of the sensor data (SD) by a classification device (12) using a predetermined classification model (11); and comparing classification results of the first and the second classification and performing a diagnosis depending on the comparison.

Claims

1. A method for performing a diagnosis of a camera system of a motor vehicle, comprising:

providing at least one image of an environmental region of the motor vehicle by a camera of the camera system;

detecting at least one object external to vehicle in the at least one image by an image processing device of the camera system;

providing sensor data by at least one sensor of the motor vehicle, wherein the sensor data characterizes environmental conditions of the motor vehicle;

first classifying the at least one object and herein associating the object with a class among a plurality of predetermined classes depending on the environmental conditions, wherein the plurality of classes differ from each other with respect to the environmental conditions,

second classifying the at least one object and herein associating the object with one of the plurality of classes based on the image, and independently of the sensor data, by a classification device using a predetermined classification model; and

comparing classification results of the first and the second classification and performing a diagnosis depending on the comparison.

2. The method according to claim 1, further comprising:

generating an error signal by the camera system, when the camera system detects that the object has been associated with a different class by the first classification than by the second classification.

3. The method according to claim 1, wherein the plurality of classes differ from each other in a brightness of the environmental region.

4. The method according to claim 1, wherein the plurality of classes differ from each other in atmospheric conditions of the environmental region.

5. The method according to claim 1, wherein the following data is provided as the sensor data:

data indicating a current operating state of a headlight of the motor vehicle, and

data indicating a current operating state of a windshield wiper of the motor vehicle, and

sensor data of a rain sensor and/or of a brightness sensor of the motor vehicle.

6. The method according to claim 1, wherein a HOG classifier and/or an SVM classifier and/or a classifier based on a classification tree method is used as the classification model.

7. The method according to claim 1, wherein an algorithm is used as the classification model, which is trained with test image data with respect to the classification.

8. The method according to claim 7, wherein the training of the algorithm includes that objects are detected in the test image data and are each associated with one of the plurality of classes depending on sensor data of at least one sensor, which characterizes environmental conditions at the time of capture of the test image data, and wherein the classified objects are taken as a basis for training the algorithm.

9. The method according to claim 7, wherein the training of the algorithm is performed in a development phase of the camera system.

10. The method according to claim 7, wherein the training of the algorithm is performed in the operation of the camera system based on image data, which is provided in the operation of the camera system by the camera.

11. A camera system for a motor vehicle, wherein the camera system is adapted to perform a method according to claim 1.

12. A motor vehicle passenger car comprising a camera system according to claim 11.