Parking Area Detection Using Lateral Distance Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting parking areas on road sections are inefficient, particularly in creating complete and up-to-date parking space maps, as they rely exclusively on detecting occupied spaces and are prone to false positives due to parked vehicles in second rows or oncoming traffic, and require extensive data collection.
Innovation Solution
A method involving a detection vehicle equipped with sensors to determine lateral distances and compare them to a known usable road width, filtering out false positives by discarding deviations and using additional localization methods when necessary, allowing for rapid creation of accurate parking space maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If parking areas are detected exclusively by detecting occupied spaces, then the detection method is simple, but the parking space map is incomplete and outdated
Solution Approach 1:
Instead of detecting parking spaces by identifying empty areas, the patent inverts the approach by detecting occupied spaces and inferring parking area locations from the patterns of vehicle placements. The system detects vehicles and uses their positions to identify where parking areas exist, rather than directly detecting empty parking spaces.
Solution Approach 2:
The patent converts the harmful effect of parked vehicles blocking sensor views into a beneficial detection mechanism. By using the vehicles themselves as detection targets and analyzing their lateral distances from the detection vehicle, the system identifies parking area boundaries and locations, turning an obstacle into a useful signal source.
2Productivity
If lateral distances are measured without filtering, then all detected areas are recorded, but false positives from second-row vehicles and oncoming traffic are included
Solution Approach 1:
The patent applies preliminary filtering actions by comparing lateral distances against expected usable road widths before finalizing parking area detections. The system pre-establishes what normal road dimensions should be and uses this knowledge to filter out anomalous detections caused by second-row vehicles or oncoming traffic before they are recorded as false parking areas.
Solution Approach 2:
The system uses feedback mechanisms by continuously comparing measured lateral distances with expected road width parameters. When measurements deviate significantly from expected values, the system adjusts its detection logic to exclude those areas, using the feedback from distance measurements to refine and correct parking area identification in real-time.
3Reliability
If extensive data collection is performed to create complete parking maps, then map completeness improves, but the number of journeys required increases
Solution Approach 1:
The patent changes the detection parameters from requiring complete coverage over multiple journeys to using lateral distance measurements that can identify parking areas in fewer passes. By measuring perpendicular distances from the detection vehicle to lateral objects and comparing these to expected road widths, the system achieves reliable detection with reduced traversal requirements.
Solution Approach 2:
The system transitions from longitudinal data collection (requiring multiple journeys along the road) to lateral dimension detection (measuring perpendicular distances during a single pass). This dimensional shift allows the system to identify parking areas by analyzing cross-sectional road geometry rather than requiring extensive longitudinal sampling over multiple trips.
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 the efficient and accurate detection of parking areas, filtering out false positives and providing a complete parking space map with fewer journeys, even in the presence of oncoming traffic, by continuously comparing determined distances to a known usable width.
Implementation Method 1
distance-based sensors (for example, ultrasonic, radar, laser, video, lidar sensors)
Implementation Method 2
distance-based sensors (for example, ultrasonic, radar, laser, video, lidar sensors)
Implementation Method 3
distance-based sensors (for example, ultrasonic, radar, laser, video, lidar sensors)
Data Source
AI summary
A method for detecting a parking area on at least one road section includes providing a usable width of the road section. The usable width represents a passable width of the road section between parking vehicles. The method further includes travelling on the road section using a detector vehicle and detecting lateral distances from objects with a detector device arranged in the detector vehicle. The method also includes comparing the detected lateral distances with the usable width, and detecting the parking area based on the comparison.