Parking Mode Selection via Multi-Feature Likelihood Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking assisting apparatuses fail to accurately determine the manner of parking in scenarios where white lines are faded, replaced, or absent, leading to incorrect parking mode selection.
Innovation Solution
A parking assisting apparatus equipped with an imaging unit, image processing section, obstacle detecting section, and manner-of-parking selecting section that integrates likelihoods based on recognized feature shapes such as white lines, tires, number plates, and obstacles to select the appropriate parking mode, including perpendicular and parallel parking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the parking assisting apparatus relies on detecting white lines to determine parking mode, then the system is simple to operate, but the reliability deteriorates when white lines are faded, replaced, or absent
Solution Approach 1:
The system performs multiple functions using the same imaging unit: it detects white lines, recognizes feature shapes (tires, number plates, obstacles), and determines positional relationships. This multi-functionality allows the system to maintain reliability across different parking scenarios without adding separate detection systems, preserving ease of operation while improving robustness.
Solution Approach 2:
The system changes the detection parameters dynamically by switching between different feature types (white lines, tires, number plates, obstacles) based on what is detectable in the current environment. When white lines are faded or absent, the system transitions to using alternative features, maintaining reliability without complicating the user interface.
2Reliability
If the system uses multiple feature recognition methods (white lines, tires, number plates, obstacles), then the reliability improves, but the device complexity increases
Solution Approach 1:
The imaging unit and image processing section serve multiple purposes: capturing images, detecting white lines, recognizing feature shapes, and determining positional relationships. This multi-functional design improves reliability through diverse detection capabilities while avoiding the complexity of multiple separate detection systems.
Solution Approach 2:
The patent combines previously separate functions (white line detection, feature shape recognition, obstacle detection) into an integrated processing pipeline. The image processing section handles all feature types uniformly, and the determination section integrates results from all sources to select parking mode, reducing overall system complexity while maintaining high reliability.
3Measurement precision
If the system integrates likelihoods from multiple sources to select parking mode, then the measurement precision improves, but the calculation complexity increases
Solution Approach 1:
The system replaces complex mechanical decision-making with a structured probabilistic framework. Instead of using intricate rules to evaluate multiple features, the system calculates likelihoods for each feature type and integrates them mathematically to determine the most probable parking mode, achieving high measurement precision with manageable calculation complexity.
Solution Approach 2:
The system uses feedback from multiple feature detections to continuously refine the likelihood calculation for each parking mode. By comparing the integrated likelihoods and selecting the mode with the highest probability, the system achieves precise determination while using a straightforward iterative calculation process that avoids excessive complexity.
Data Source
AI summary
A parking assisting apparatus includes an imaging unit acquiring image information corresponding to an image of surroundings of a vehicle, an image processing section recognizing a feature shape in the image by processing the image information, an obstacle detecting section acquiring positional-relationship information corresponding to a positional relationship between the vehicle and an obstacle present around a parking space, and a manner-of-parking selecting section selecting a manner of parking the vehicle in the parking space from manner candidates including perpendicular parking and parallel parking based on the feature shape and the positional-relationship information. The manner-of-parking selecting section selects the manner of parking from the manner candidates by integrating a likelihood of each of the manner candidates based on the positional-relationship information with a likelihood of the manner candidate based on a recognition result to calculate final likelihoods of the respective manner candidates, and by comparing the calculated final likelihoods.