Stereo Side Camera Lateral Control for Tight Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems face challenges in accurately measuring and navigating tight parking spaces, especially in urban areas, due to limitations of ultrasonic, radar, and LIDAR sensors when dealing with absorbing media or objects outside their detection cone, and video cameras struggle with precise lateral control.
Innovation Solution
A method utilizing a side camera to capture stereo images, calculating 3D distances, and determining the ratio of these distances for lateral control, enabling precise steering commands for navigating tight spaces, including parking and maneuvering in crowded areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasonic sensors, radar sensors or LIDAR sensors are used for measuring parking spaces, then measurement capability is provided, but they fail when there are absorbing media in the environment or when objects are outside the detection area
Solution Approach 1:
The patent combines multiple sensor types (ultrasonic, radar, LIDAR, and video cameras) into a hybrid sensor system. This merging allows the system to leverage the strengths of each sensor type while compensating for their individual weaknesses, particularly using video cameras to detect objects that absorbing media or cone-shaped sensors cannot detect.
Solution Approach 2:
The sensor system is designed to perform multiple detection functions using different sensor types. Video cameras serve as a universal detection method that can detect various objects (vehicles, pedestrians, cyclists, animals) in situations where specialized sensors like ultrasonic or radar fail, providing universal coverage across all detection scenarios.
2Area of stationary object
If video cameras are used to monitor lateral environment, then detection coverage is improved, but precise lateral control and distance measurement become difficult
Solution Approach 1:
The patent uses stereo vision technology as an intermediary method to bridge the gap between video camera detection coverage and precise distance measurement. By capturing images from two different positions (stereo bases) and calculating the ratio of distances, the system derives accurate lateral distance information from visual data without requiring direct contact with the objects being measured.
3Ease of operation
If assisted or semi-automatic driving is implemented, then parking process support is provided, but driver control and decision-making are reduced
Solution Approach 1:
The driving assistance system is designed to dynamically adjust the level of automation based on the situation. The system can operate in assisted mode where the driver maintains full control, semi-automatic mode where the system takes over certain functions, or fully automatic mode for complete automation, allowing flexible adaptation to different parking scenarios and driver preferences.
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 allows for improved lateral control and navigation in tight spaces, maintaining defined distances and facilitating easy entry and exit from vehicles, even in complex parking scenarios, by creating a time-parameterized 3D model of the environment for real-time vehicle guidance.
Implementation Method 1
a side camera of the vehicle captures an area around the vehicle and first images from the side camera are selected for a first stereo basis
Implementation Method 2
first 3D information is determined from the first images and a first distance of the vehicle from an object in the area surrounding the vehicle is calculated
Data Source
Figure 1
Figure 2~3
AI summary
The invention relates to a method for driving assistance with a side camera (1, 22) that captures an environment of the vehicle (20). Two respective images of the side camera are combined into a first or second stereo basis (29, 30). A first and a second distance (32, 33) are determined on the basis of the images. The transverse guidance takes place on the basis of the ratio between the first and the second distances (32, 33). The method can be used in particular for parking. The invention also relates to a driving assistance system, in particular for performing the method.