Vehicle Vision Gatekeeper for Safe Object Distance Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vision systems for motor vehicles require extensive and costly software development to achieve high functional safety levels for object detection, making it inefficient and expensive to use detected objects in safety-critical applications like automatic emergency braking.
Innovation Solution
Implementing a small gatekeeper code module with a higher safety level quality, which evaluates detected objects using verified depth or disparity images, to ensure only safe objects are used in safety-critical applications, thereby reducing the amount of code requiring high functional safety levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the complete object detection code is written with higher functional safety level quality, then the safety and reliability of detected objects in safety-critical applications is improved, but the development cost and manpower requirements increase significantly
Solution Approach 1:
The patent segments the object detection system into two distinct parts: a first object detection code operating at non-critical safety levels for general object detection, and a second object detection code operating at higher functional safety levels for verifying specific detected objects. This segmentation allows the majority of code to remain at lower complexity while only critical verification portions require high safety standards, thereby resolving the contradiction between reliability and code complexity.
2Reliability
If the complete object detection code is written with higher functional safety level quality, then the safety and reliability of detected objects in safety-critical applications is improved, but the development cost and manpower requirements increase significantly
Solution Approach 1:
The patent segments the object detection system into two distinct parts: a first object detection code operating at non-critical safety levels for general object detection, and a second object detection code operating at higher functional safety levels for verifying specific detected objects. This segmentation allows the majority of code to remain at lower complexity while only critical verification portions require high safety standards, thereby resolving the contradiction between reliability and code complexity.
Data Source
AI summary
A vision system (10) for a motor vehicle includes an imaging apparatus (11) adapted to capture images from a surrounding of the motor vehicle, and a processing device (14) adapted to execute an object detection code (15) to detect objects in the surrounding of the motor vehicle by processing images captured by the imaging apparatus (11), and to calculate for each detected object its longitudinal distance relative to the ego vehicle. The vision system includes a gatekeeper code module (33) having a higher functional safety level than the object detection code (15). The gatekeeper code module (33) takes as input objects (32) detected by the object detection code (15) and evaluates if a depth or disparity image (35), in at least a part of an area covering the detected object (32), matches within given tolerances the longitudinal distance of the detected object (32) given by the object detection code (15).