System and method for fault detection and correction

Patent metadata

Field	Value
Publication number	US-11470245-B2
Application number	US-202016822976-A
Country	US
Kind code	B2
Filing date	Mar 18, 2020
Priority date	May 1, 2019
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

A method for detecting and correcting transient faults, the method the steps of comprising obtaining (110) image data from a camera system, and processing (120) image data using a first image signal processor and a second image signal processor, to produce first and second output data. At least one statistical model is generated (130) based on at least the first and second output data and used to identify (140) whether a fault is present in the first output data. A correction value for the portion of image data is generated (150), wherein the correction value is an expected value based on the statistical models, and used to generate (160) updated output data. The updated output data is then outputted (170) to an output device.

First claim

What is claimed is:

1. A method for detecting and correcting transient faults, the method the steps of comprising:
obtaining image data from a camera system;
processing image data using a first image signal processor and a second image signal processor, to produce first and second output data;
generating at least one statistical model based on at least the first and second output data;
identifying whether a fault is present in the first output data based on the statistical models;
generating a correction value for the portion of image data wherein the correction value is an expected value based on the statistical models;
generating updated output data using the correction value; and
outputting the updated output data to an output device.

2. The method of claim 1 , wherein generating the at least one statistical model is further based on previous image data obtained by the camera system, and at least one real-world reference image.

3. The method of claim 1 , wherein the step of processing the image data comprises processing a portion of the image data obtained by the camera system.

4. The method of claim 1 , wherein generating the correction value comprises applying at least one machine learning algorithm to the output to generate an expected value for the fault using the at least one statistical model.

5. The method of claim 1 , wherein the step of generating updated output data comprises combining the correction value with the first output data.

6. The method of claim 1 , wherein the step of generating updated output data comprises comparing a portion of the second output data corresponding to the fault in the first output data, with the correction value, and where the portion substantially corresponds to the correction value, setting the updated output data to be the second output data.

7. A safety critical system comprising:
a camera system for obtaining image data relating to a system environment;
at least two image signal processors each for processing the image data received from the camera system and generating a first output and a second output;
a fault detection and correction module, for detecting one or more faults in the first output, and generating updated output data wherein the updated output data comprises a corrected fault, the corrected fault generated using at least statistical model based on the first output and second output; and
an output device for receiving the updated output data from the fault detection and correction module.

8. The safety critical system of claim 7 , wherein the fault detection and correction module comprises:
a statistical model unit for generating at least one statistical model based on the first output and second output;
a fault determination unit for determining whether there is a fault in first output; and
an output generation unit for generating updated output data, the updated output data comprising an expected value generated by the statistical models.

9. The safety critical system of claim 8 , wherein the fault detection and correction module further comprises a combination unit for combining the expected value with the first output data.

10. The safety critical system of claim 8 , wherein the fault detection and correction module further comprises a comparison unit for comparing the expected value with a portion of the second output corresponding to the fault in the first output data, and if the portion of the second output data is substantially similar to the expected value, outputting the second output data.

11. The safety critical system of claim 7 , wherein the output device is a processor, for processing the output of the fault detection and correction module.

12. The safety critical system of claim 7 , wherein the fault detection and correction module comprises at least one machine learning processor.

13. A non-transitory computer readable storage medium comprising a set of computer-readable instructions stored thereon which, when executed by at least one processor cause the processor to detect and correct errors in a safety critical system, the instructions comprising:
obtaining image data from a camera system;
processing image data using a first image signal processor and a second image signal processor, to produce first and second output data;
generating at least one statistical model based on at least the first and second output data;
determining whether a fault is present in the first output data based on the statistical models;
generating a correction value for the portion of image data wherein the correction value is an expected value based on the statistical models;
generating updated output data using the correction value; and
outputting the updated output data to an output device.

14. An autonomous vehicle comprising:
at least one camera system; and
a processor arranged to undertake the method of claim 1 .

Assignees

• Apical Ltd
• Advanced Risc Mach Ltd

Inventors

• Dewhurst Andrew
• Hanwell David

Classifications

• H04N25/60 Primary

  Noise processing, e.g. detecting, correcting, reducing or removing noise · CPC title

• H04N23/64 Primary

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• G06T7/001 Primary

  using an image reference approach · CPC title

• B60R2001/1253

  with cameras, video cameras or video screens · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title