Parking Assist Target Positioning Across Uneven Parking Planes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking assist systems face challenges in accurately determining the target parking position when the vehicle and parking frame are not on the same plane, leading to deformation of the parking frame shape in images and inappropriate parking calculations.
Innovation Solution
A parking assist system that uses a combination of cameras and ultrasonic sensors to detect parking frames and spaces, determining the accuracy of the parking frame and calculating the target parking position based on the detected accuracy, switching between camera and sonar data to ensure accurate positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera-based parking frame detection is used, then parking frame shape and position can be visually identified, but measurement precision deteriorates when vehicle and parking frame are not on the same plane
Solution Approach 1:
The patent combines camera-based parking frame detection with ultrasonic sensor-based parking space detection. When the parking frame detection accuracy is determined to be low (indicating the vehicle and parking frame are not on the same plane), the system merges in ultrasonic data to calculate the target parking position, thereby maintaining measurement precision across different plane conditions.
Solution Approach 2:
The system dynamically changes the detection parameters by switching between camera-only mode and combined camera-ultrasonic mode based on the detected accuracy of the parking frame. This parameter change allows the system to adapt to different plane conditions while maintaining accurate parking position calculation.
2Reliability
If ultrasonic sensors are used for parking space detection, then measurement reliability improves in varying plane conditions, but device complexity increases
Solution Approach 1:
The patent implements a dynamic sensor activation strategy where ultrasonic sensors are selectively engaged based on the detected accuracy of camera-based parking frame detection. When accuracy is low, ultrasonic sensors are activated to provide reliable parking space measurement; when accuracy is high, only camera sensors are used. This dynamic approach improves reliability while minimizing device complexity by avoiding continuous use of all sensors.
3Measurement precision
If multiple detection methods are combined, then parking position accuracy is maintained across different conditions, but processing time increases
Solution Approach 1:
The system performs preliminary detection using the camera to assess parking frame accuracy before determining whether ultrasonic sensor data is needed. This preliminary action allows the system to quickly evaluate conditions and only engage additional sensors when necessary, thereby maintaining high measurement precision while minimizing the time lost to processing.
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
The system effectively reduces errors in parking target position calculation by using sonar data when camera-based frame accuracy is low and camera data when accuracy is high, ensuring appropriate parking positioning.
Implementation Method 1
detect a parking space based on ultrasonic transmitted waves and reflected waves of the ultrasonic transmitted waves
Data Source
AI summary
A parking assist system according to an embodiment includes a processor connected to a memory. The processor detects a parking frame around a vehicle based on a photographed image obtained by photographing surroundings of the vehicle. The processor detects a parking space based on ultrasonic transmitted waves and reflected waves of the ultrasonic transmitted waves. The processor determines accuracy of the parking frame. The processor determines, based on the accuracy of the parking frame, a method of calculating a target parking position using the parking frame and the parking space. The processor calculates the target parking position based on the determination on the method of calculating the target parking position. The processor generates a route based on the target parking position.