Ultrasonic Parking Edge Detection Curb Plausibility Check
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking systems face challenges in accurately detecting the edges of parking spaces due to scattering of edge detection, leading to errors where objects appear to still be present when the space begins, resulting in shortened perceived parking spaces.
Innovation Solution
The method incorporates a plausibility check using both the signal curve of distance signals from objects delimiting the parking space and the curb, utilizing higher echoes to determine the curb's course and adjust edge detection accordingly, ensuring the edge is accurately positioned within the visible curb area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If edge detection is performed using only distance signals from objects delimiting the parking space, then the detection process is simple, but the accuracy of edge detection deteriorates due to scattering and false detection
Solution Approach 1:
The patent introduces a curb signal as an intermediary reference for plausibility checking. The curb signal acts as a mediator between the raw distance signals and the final edge detection result, providing a reference framework to validate whether detected edges are physically plausible. This intermediary layer filters out false detections caused by scattering while maintaining the overall simplicity of the detection process.
Solution Approach 2:
The patent implements a feedback mechanism where the detected edge position is checked against the curb signal profile. If the detected edge falls outside the visible curb area or creates physical inconsistencies, the system uses the curb signal feedback to correct or reject the detection. This feedback loop significantly improves edge detection accuracy without requiring complex additional hardware.
2Measurement precision
If higher echoes are used to determine the curb course, then the accuracy of curb positioning is improved, but the processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary processing of higher echoes to establish the curb course profile before actual edge detection occurs. By pre-processing the curb signal and storing it as a reference framework, the system avoids the need to analyze all higher echoes in real-time during edge detection. This preliminary action significantly reduces processing time while maintaining high curb positioning accuracy.
Solution Approach 2:
The patent selectively uses higher echoes only in the regions where the curb is expected to be visible, rather than processing all echo data comprehensively. By focusing computational resources on the relevant partial area where curb detection is needed, the system achieves high positioning accuracy without the excessive processing time that would result from analyzing all possible echo paths.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances system accuracy by better utilizing sensor data, reducing edge detection scattering and improving the utilization of available parking spaces, especially in tight spaces, thereby enhancing the overall parking system's performance.
Implementation Method 1
ultrasonic sensors for measuring and detecting objects delimiting a parking space and a curb or a curb edge
Implementation Method 2
signal curve of distance signals from objects delimiting a parking space
Data Source
Figure 1~2
Figure 3
AI summary
A method for edge detection of objects bounding a parking space (01) using preferably ultrasonic sensors (Ultrasonic Park Assist Sensors; UPA sensors) is described. In this method, a signal profile of distance signals from the objects (02) bounding the parking space (01) is determined. The plausibility of the edge detection is then verified using a curb signal. This is achieved by considering not only the signal profile of the distance signals from the objects (02) bounding the parking space (01) but also the signal profile of the distance signals from a curb (03) for plausibility checks. Furthermore, a driver assistance device for carrying out the method and a computer program product are described, which instructs a microprocessor with associated memory to execute the method.