Road Sign Recognition Using Main-Auxiliary Sign Combinations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing road sign recognition systems struggle to accurately determine vehicle control content due to misrecognition of auxiliary signs, which often have smaller characters or patterns, making it difficult to correctly interpret the combined regulation content of main and auxiliary signs.
Innovation Solution
A road sign recognition device that includes an image acquisition unit, a road sign recognition unit, a road sign data recording unit, and a vehicle control information determination unit, which uses combination information stored in the data recording unit to accurately identify auxiliary signs based on their relationship with main signs, improving recognition performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image recognition technology is used to recognize road signs, then recognition accuracy can be improved, but processing time increases causing delays in providing recognition results
Solution Approach 1:
The image processing is divided into multiple stages: first extracting candidate regions using road sign characteristics (color, shape, position), then performing detailed recognition only on these candidates. This segmentation allows the system to maintain high recognition accuracy while significantly reducing overall processing time by avoiding full-image analysis.
Solution Approach 2:
The system performs preliminary filtering and candidate region extraction before final recognition. By pre-identifying potential road sign locations and characteristics, the system prepares data in advance, enabling faster and more accurate recognition without requiring complete image processing.
2Reliability
If multiple types of sensors are used to detect road signs, then detection reliability can be improved, but device complexity increases
Solution Approach 1:
The system employs a camera as a multi-functional sensor that performs multiple detection tasks: identifying road signs, determining their positions, and recognizing their types. This universal approach achieves reliable detection without requiring separate specialized sensors for each function, thereby reducing overall system complexity.
Solution Approach 2:
The image recognition system processes and interprets visual data independently, extracting meaningful information directly from images without requiring additional sensor inputs or complex sensor fusion algorithms. The system serves itself by making the camera's visual data sufficient for all detection needs.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The purpose of the present invention is to correctly determine details of control of a vehicle on the basis of the recognition result of a road sign. A road sign recognition device 10 is provided with: an image acquisition unit 101 that acquires an image; a road sign recognition unit 102 that recognizes a road sign from the image acquired by the image acquisition unit 101; a road sign data recording unit 103 that stores road sign information about a combination of a plurality of road signs; and a vehicle control information determination unit 104 that determines vehicle control information used for controlling a host vehicle. The vehicle control information determination unit 104 determines the vehicle control information on the basis of the road sign recognition result of the road sign recognition unit 102 and the road sign information stored in the road sign data recording unit 103.