CNN Image Range Detection for Autonomous Driving Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image analysis software in autonomous driving systems may incorrectly analyze image data in adverse weather conditions or extreme lighting, leading to unreliable object detection and road marking recognition.
Innovation Solution
A system and method that use a convolutional neural network (CNN) to determine whether image data is within a predetermined range that the image analysis software is configured to analyze, by calculating perturbation values and comparing confidence values between original and perturbed image data predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If image analysis software is used to analyze image data in adverse weather conditions or extreme lighting, then the system can maintain autonomous functionality, but the reliability of object detection and road marking recognition deteriorates
Solution Approach 1:
The system performs preliminary analysis by generating adversarial examples and calculating confidence values before actual image analysis. By pre-computing perturbation values and comparing confidence scores, the system determines in advance whether the image data falls within the reliable analysis range, preventing unreliable predictions from occurring in the first place
Solution Approach 2:
The system implements a feedback mechanism where confidence values from adversarial example analysis are used to determine whether to trust the main image analysis results. The confidence comparison provides feedback that guides the decision-making process, allowing the system to adjust its behavior based on the reliability assessment
2Reliability
If the system disables autonomous functionality when image data is outside the predetermined range, then the reliability of operation is improved, but the productivity and usability of the autonomous driving system deteriorates
Solution Approach 1:
The system changes the parameter being monitored from direct image quality metrics to confidence value differences between original and perturbed images. By transforming the reliability assessment into a confidence comparison task, the system can make more accurate determinations about when to disable functionality, reducing false positives that would unnecessarily limit autonomous operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system for determining whether image data is within a predetermined range that image analysis software is configured to analyze. The system includes a camera and an electronic processor. The electronic processor is configured to receive the image data from the camera and generate a prediction regarding the image data and a confidence value associated with the prediction. The electronic processor is also configured to perturb the image data using a perturbation value and generate a prediction regarding the perturbed image data and a confidence value associated with the prediction. The electronic processor is further configured to compare the confidence values and disable autonomous functionality of a vehicle when the difference between the confidence value associated with the prediction regarding the image data and the confidence value associated with the prediction regarding the image data is less than a predetermined threshold value.