In-Vehicle Image Processing for Parkable Area Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing in-vehicle image processing devices for parking assistance rely on recognizing a vehicle's license plate to determine parkable areas, which fails when a license plate is missing or not recognizable, such as in vehicles without a license plate or when the plate cannot be identified.
Innovation Solution
An in-vehicle image processing device that generates an overhead image of the road surface, recognizes tires and three-dimensional objects, calculates the ground contact position of tires, and identifies areas under vehicles to determine non-parkable spaces, thereby recognizing parkable areas without relying on license plate recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If license plate recognition is used to determine parkable areas, then the determination process is simplified, but the system fails when license plate is missing or not recognizable
Solution Approach 1:
The patent introduces tire recognition as an intermediary method to bridge the gap when license plate recognition fails. By recognizing tires and calculating their ground contact positions, the system can determine vehicle boundaries and parkable areas through an alternative pathway, ensuring continuous operation even when the primary license plate recognition method is unavailable
Solution Approach 2:
The patent changes the recognition parameter from license plate features to tire features. Instead of relying on text or graphical patterns on the license plate, the system switches to recognizing circular shapes, patterns, and positions of tires, fundamentally changing the detection parameter to maintain reliability under different conditions
2Reliability
If tire recognition and three-dimensional object recognition are added to improve reliability, then the system can work without license plates, but the device complexity increases
Solution Approach 1:
The patent designs the image processing device with multi-functional capabilities where the same camera and processing unit can perform license plate recognition, tire recognition, and three-dimensional object recognition. This universal approach allows the system to adapt between different recognition methods without requiring entirely separate hardware systems, thereby managing complexity while maintaining reliability
Solution Approach 2:
The patent segments the recognition tasks into distinct functional modules: license plate recognition module, tire recognition module, and three-dimensional object recognition module. Each module can operate independently, allowing the system to activate only the necessary modules based on detection conditions, thus managing computational complexity while ensuring reliability through redundant capabilities
3Measurement precision
If overhead image generation and area calculation are implemented to recognize parkable areas accurately, then parking position recognition is improved, but processing time and computational load increase
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing standard vehicle dimensions, tire patterns, and overhead image transformation parameters. When processing actual images, the system retrieves these pre-computed data and applies them directly, significantly reducing real-time processing time while maintaining precise parkable area recognition
Solution Approach 2:
The patent implements partial processing by focusing computational resources on critical areas only. Instead of processing the entire image at full resolution, the system identifies regions containing tires or vehicles and performs detailed analysis only on those areas, using lower resolution for background regions, thus reducing overall processing time while maintaining measurement precision where it matters most
Data Source
AI summary
An in-vehicle image processing device processes camera images to determine a parkable area and includes an overhead image generation section generating an overhead image relative to a road surface by converting the view point of an image of a nearby vehicle and the road surface taken by a vehicle-mounted camera; a tire recognition section recognizing the tires of the nearby vehicle; a three-dimensional object recognition section recognizing three-dimensional objects including the nearby vehicle; an area-under-vehicle recognition section calculating the ground contact position of the tire and the above-ground height from the ground contact position to the vehicle body and recognizing an area under the vehicle body on the road surface from the overhead image; and a parkable area recognition section for recognizing the area occupied by the vehicle body and the area under the vehicle body as a non-parking area and recognizing a parkable area on the road surface.