Traffic Sign-Based Road Edge Detection in Obscured Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems (ADAS) and autonomous vehicles face challenges in detecting the road edge and plane, especially in adverse conditions such as snow, drifting sand, or heavy leaf coverage, leading to unsatisfactory performance or failure.
Innovation Solution
The system employs processors to recognize roadside traffic signs, utilizing stored sign information to determine the likely location of the road edge relative to the vehicle, and sends control signals based on this determination, enhancing road edge detection accuracy even in obscured conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor-based techniques (cameras, LIDAR, radar) are used to detect road edge and plane, then the system can automate vehicle navigation and improve safety, but the detection performance deteriorates in adverse conditions such as snow, drifting sand, or heavy leaf coverage
Solution Approach 1:
The patent introduces traffic signs as intermediary objects that are less affected by adverse environmental conditions. Instead of directly detecting the obscured road edge, the system detects traffic signs (which remain visible) and uses their known spatial relationships to road edges to infer road edge locations. This intermediary approach bypasses the harmful effect of snow, sand, or leaves obscuring the direct detection path.
Solution Approach 2:
The system performs preliminary detection of traffic signs and their types before using this information to determine road edge locations. By first identifying the traffic sign and querying its pre-stored spatial relationship data to road edges, the system prepares the necessary information in advance, enabling accurate road edge detection even when direct visualization is blocked by adverse conditions.
2Measurement precision
If the system analyzes the entire image to detect road edges, then it can cover all possible areas, but the processing time and computational resources increase
Solution Approach 1:
The patent segments the image processing task by first detecting traffic signs and then focusing road edge detection only in the specific regions around these signs. Instead of analyzing the entire image uniformly, the system divides the processing into targeted zones based on traffic sign locations, significantly reducing the computational area while maintaining detection accuracy.
Solution Approach 2:
The system performs preliminary detection of traffic signs and queries their pre-stored spatial relationship information to road edges before conducting detailed road edge analysis. This preliminary action provides prior knowledge about where to focus the detection efforts, eliminating the need to scan the entire image and reducing processing time while maintaining precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In some examples, one or more processors of a vehicle may store, in a computer-readable medium, sign information relating a sign type of a traffic sign to a distance to a road edge for a plurality of sign types. The one or more processors may receive at least one image from at least one sensor, and may recognize a sign type of a traffic sign in the at least one image. Further, the one or more processors may determine a likely location of a road edge in relation to the vehicle based at least partially on the recognized sign type and the stored sign information. In some examples, the one or more processors may send one or more control signals to at least one component of the vehicle based on the determined likely location of the road edge relative to the vehicle.