Vehicle Identification via License Plate Perspective Rectification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motor vehicle identification systems for traffic monitoring are complex and require multiple recordings or sensors due to sensitivity to alignment, illumination, and weather conditions, leading to potential errors and increased material and evaluation complexity.
Innovation Solution
A method and apparatus that record a motor vehicle's image at an acute angle, recognize and rectify the license plate contour, and use similarity comparison with standardized formats to categorize vehicles independently of exact camera alignment, reducing complexity by extracting and adapting the image region around the license plate for perspective rectification and comparison with database images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple recordings or sensors are used to capture vehicle features, then identification reliability is improved, but device complexity and material requirements increase
Solution Approach 1:
The patent extracts and focuses solely on the license plate region from the vehicle image, rather than capturing multiple vehicle features using multiple sensors. By isolating the license plate contour and performing recognition only on this extracted region, the system achieves reliable identification with minimal sensor requirements, directly resolving the contradiction between reliability and device complexity
Solution Approach 2:
The patent segments the vehicle image into relevant and irrelevant regions, focusing computational resources only on the license plate area. This segmentation allows the system to maintain high identification reliability through targeted processing while reducing overall device complexity by ignoring non-essential vehicle features
2Measurement precision
If multiple sensors are used to capture vehicle features, then measurement precision is improved, but evaluation complexity increases
Solution Approach 1:
The patent extracts only the license plate contour from the image and performs all recognition and measurement operations on this isolated region. This extraction eliminates the need to process multiple vehicle features simultaneously, maintaining measurement precision for license plate recognition while significantly reducing evaluation complexity
Solution Approach 2:
Instead of processing complete vehicle images or multiple sensor inputs to achieve precision, the patent inverts the approach by pre-processing to isolate only the critical license plate region before recognition. This inversion of the processing sequence achieves precise measurement with simpler evaluation
3Measurement precision
If camera alignment is required for accurate vehicle identification, then measurement precision is improved, but adaptability to different positions decreases
Solution Approach 1:
The patent employs dynamic perspective rectification that automatically adapts to different camera angles and positions. The system calculates and applies appropriate transformation rules based on the actual image geometry, allowing precise license plate recognition regardless of whether the camera is positioned directly above, at an angle, or from the side, thus achieving both precision and adaptability
Solution Approach 2:
The patent changes the geometric parameters of the license plate contour through perspective transformation, converting it into a standardized format that can be recognized accurately regardless of the original camera position. By dynamically adjusting these geometric parameters, the system maintains measurement precision across varying adaptability conditions
Data Source
AI summary
A method and an apparatus for identifying motor vehicles for monitoring traffic. The identification is carried out by image-evaluation and includes determining the size ratios of a license-plate contour in a perspectively distorted image on the basis of stored standardized license-plate formats, determining the size of the perspective distortion of the license-plate contour on the basis of the associated standardized license-plate format, establishing a calculation rule for the perspective rectification on the basis of the ascertained distortion of the license-plate contour with respect to the associated license-plate format, rectifying the extracted license-plate-containing motor-vehicle view, and comparing the rectified image with reference images of front views of motor vehicles stored in a database in order to assign the image with greatest correspondence to a group of classified motor vehicles.