Road Sign Recognition Using Motion Blur Subtraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver assistance systems face challenges in reliably recognizing road signs with variable text components due to motion blur in images captured by vehicle cameras, especially at night or in low light conditions, where image resolution and sharpness are insufficient.
Innovation Solution
A method that involves acquiring images of road signs, determining and subtracting motion blur from the image segments containing the signs, and then recognizing the signs using pattern or text recognition techniques on the sharpened segments, utilizing camera systems like mono or stereo cameras with CMOS or CCD sensors, and vehicle motion data for accurate blur estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a camera in a moving vehicle captures road signs, then the system can recognize road signs, but motion blur reduces image sharpness and resolution making text recognition difficult
Solution Approach 1:
The system performs preliminary actions by capturing multiple images before the actual recognition moment, using different exposure times. At least one image is captured with a longer exposure time to ensure sufficient light capture, while another is captured with a shorter exposure time to minimize motion blur. This preliminary capture of multiple images with varying exposure characteristics enables subsequent processing to select or combine the optimal image for text recognition, thereby resolving the contradiction between reliability and sharpness.
2Illumination intensity
If the camera uses a longer exposure time to capture images in low light conditions, then image brightness is improved, but motion blur increases reducing text readability
Solution Approach 1:
The imaging process is segmented into multiple captures with different exposure times. The system divides the imaging task into at least two separate image acquisitions: one with longer exposure for brightness and one with shorter exposure for sharpness. This segmentation allows the system to obtain multiple image versions that can be evaluated and selected based on their respective quality characteristics, thereby resolving the trade-off between brightness and sharpness.
Solution Approach 2:
The system changes the exposure time parameter between multiple image captures. By varying this critical imaging parameter, the system generates images with different brightness-sharpness characteristics. The evaluation unit then assesses these images and selects the one with optimal text readability, effectively using parameter variation to overcome the fixed trade-off between brightness and sharpness.
3Measurement precision
If the camera uses a shorter exposure time to reduce motion blur, then image sharpness is improved, but image brightness decreases making recognition difficult
Solution Approach 1:
The system performs preliminary actions by capturing multiple images before the actual recognition moment, using different exposure times. At least one image is captured with a longer exposure time to ensure sufficient light capture, while another is captured with a shorter exposure time to minimize motion blur. This preliminary capture of multiple images with varying exposure characteristics enables subsequent processing to select or combine the optimal image for text recognition, thereby resolving the contradiction between reliability and sharpness.
Solution Approach 2:
The system changes the exposure time parameter between multiple image captures. By varying this critical imaging parameter, the system generates images with different brightness-sharpness characteristics. The evaluation unit then assesses these images and selects the one with optimal text readability, effectively using parameter variation to overcome the fixed trade-off between brightness and sharpness.
4Measurement precision
If the system captures multiple images with different exposure times, then image quality options increase, but processing time and complexity increase
Solution Approach 1:
The evaluation unit performs self-service by automatically assessing the captured images and selecting the optimal one for text recognition without requiring manual intervention or complex external processing. The system uses automated image quality evaluation metrics to quickly determine which image provides the best text readability, thereby minimizing processing time while maintaining high image quality selection.
Data Source
AI summary
The invention relates to a method and a device for recognizing a road sign (Hz, Zz) by means of a camera from a traveling vehicle. The method has the following steps:acquiring at least one image of the surroundings of a vehicle by means of the camera,determining the presence of at least one road sign (Hz, Zz) in the at least one acquired image of the surroundings of the vehicle,determining (also estimating) motion blur in that image segment in which the present road sign (Hz, Zz) is situated,subtracting out motion blur in this image segment, which results in a sharpened image segment, andrecognizing the road sign (Hz, Zz) while taking account of the sharpened image segment.