Vehicle Parking Detection via Radar Cluster Border Lines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle environmental detection systems are inefficient and complicated in detecting available parking spaces, especially when rows of parked vehicles are partially covered or merged with road borders, and require reference points, which limits their effectiveness in various conditions such as different movement directions, velocities, and occupied parking spots.
Innovation Solution
A vehicle environmental detection system with a radar system that forms clusters of detections, creates parallel border lines to define parking rows, and determines the orientation and gaps between vehicles, allowing for efficient detection of available parking spots without relying on specific reference points or vehicle movement parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional radar systems use Doppler effect to detect obstacles, then single targets can be distinguished, but the system becomes complicated and inefficient when detecting parking rows
Solution Approach 1:
The patent extracts and removes the requirement for reference points from the detection system. By forming clusters of detections and creating border lines directly from detection data without needing external reference points, the system simplifies the detection process while maintaining effectiveness in various movement conditions.
Solution Approach 2:
The patent segments the detection process into distinct steps: forming clusters of detections, creating parallel border lines, determining orientation, and identifying gaps. This segmentation allows each step to be processed independently and efficiently, improving overall productivity without increasing system complexity.
2Measurement precision
If reference points are used for detecting parking rows, then detection accuracy may improve, but the system becomes limited in different movement directions and velocities
Solution Approach 1:
The patent creates a universal detection method that works across multiple movement conditions without requiring adjustment for reference points. The cluster-based approach with parallel border lines can detect parking rows regardless of the ego vehicle's movement direction or velocity, making the system adaptable to various scenarios including parallel parking, angled parking, and curved paths.
3Measurement precision
If the detection system processes detailed environmental data, then detection accuracy improves, but the processing time and complexity increase
Solution Approach 1:
The patent performs preliminary clustering of detections and establishes parallel border lines as intermediate structures before final parking row identification. This preliminary organization of data reduces the computational burden in subsequent processing steps, allowing accurate detection without excessive processing time.
Solution Approach 2:
The patent focuses processing on the essential features needed for parking row detection - forming clusters and parallel border lines - rather than processing all possible environmental data. This partial action approach maintains detection accuracy while reducing processing time by concentrating computational resources on the most relevant detection aspects.
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
Enables fast, uncomplicated, and robust detection of parking rows and available spaces, independent of vehicle movement direction, velocity, and occupied spots, providing accurate orientation information and identifying gaps for parking.
Implementation Method 1
a radar system is usually arranged to distinguish or resolve single targets from the surroundings by using a Doppler effect in a previously well-known manner
Data Source
AI summary
A vehicle environmental detection system (3) in an ego vehicle (1) including at least one control unit arrangement (15) and at least one detector arrangement (4, 7) that is adapted to obtain a plurality of detections (14). The control unit arrangement (15) is adapted to form a cluster (40) of the plurality of detections (14), form a first border line (16) and a second border line (17), where these border lines (16, 17) have mutually longitudinal extensions, and are mutually parallel and define outer borders of the cluster (40) and determine whether the cluster (40) corresponds to a row (13) of corresponding parked vehicles (18a, 18b, 18c, 18d, 18e, 18f, 18g), by the length or longitudinal displacement of, or distance between, the border lines (16, 17).