Parking Space Detection Using Cluster Analysis and Frequency Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems fail to reliably distinguish between free parking spaces where parking is not permitted and permissible parking areas, often misidentifying spaces due to limitations in sensor technology and static map data.
Innovation Solution
A method utilizing vehicle surroundings sensors to detect and categorize parking spaces, assigning a function based on detection frequency and vehicle passage data, and employing cluster analysis to differentiate between free spaces and parking areas by evaluating sensor data and determining probabilities of permissible parking spaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If vehicle sensors are used to detect possible parking spaces, then the quantity of detected parking spaces increases, but the reliability of distinguishing free spaces from permissible parking areas deteriorates
Solution Approach 1:
The patent combines data from multiple vehicles passing through the same street portion to create a collective detection record. By merging individual sensor detections into a centralized database and applying cluster analysis, the system aggregates quantity information while using statistical patterns to improve reliability of classification between free spaces and permissible parking areas.
Solution Approach 2:
The system implements feedback through cluster analysis that evaluates detection frequency and vehicle passage data. The cluster analysis processes feedback from multiple detection events and uses this information to refine the classification of parking spaces, adjusting the distinction between free spaces and permissible parking areas based on accumulated evidence from multiple vehicle passages.
2Measurement precision
If cluster analysis is performed on all detected parking spaces, then the accuracy of identifying permissible parking areas improves, but the processing time and computational complexity increase
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing detection data from multiple vehicles in a database during their normal operation. This preliminary data accumulation occurs in the background without requiring real-time processing, allowing the cluster analysis to work on pre-organized data when identification is needed, thereby reducing actual processing time while maintaining high accuracy.
3Reliability
If more vehicles transmit detection data to the central computer facility, then the reliability of parking space identification improves, but the data transmission volume and processing load increase
Solution Approach 1:
The system extracts only the essential detection information from each vehicle - specifically the detection status (presence or absence of parking space) and basic vehicle passage data - rather than transmitting complete sensor datasets. This extraction approach maintains the reliability benefits of multi-vehicle data aggregation while significantly reducing the data transmission volume to the central computer facility.
Data Source
AI summary
A method for identifying free spaces (parking not permitted) and/or permitted parking areas, vehicles transmitting pieces of information about possible parking spaces (PPS) to a central computer facility (CCF). Positions of PPS are detected with vehicle surroundings sensors, and the detected PPS are evaluated based on the data collected, a categorization being performed for recording the PPS, with positions, in a CCF database and evaluating the data using a cluster analysis. When the analysis is performed, PPS are assigned to a street portion, a function is assigned to the street portion, which is given by the quotient of the frequency of PPS detections in a certain position along the street portion and the number of vehicle passages through the street portion and a weighting factor from the evaluation. A free space is inferred when the function value is greater than a predefined second limiting value and/or a parking area is inferred when the function value is within a predefined range. Also described is a device for assisting a driver, a central computer facility, and a related computer program.