Vehicle Speed Limit Determination via Sign Recognition and Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for determining the speed limit on a road taken by a motor vehicle are often imprecise, as they rely on navigation data that may be outdated or unavailable, and image processing systems struggle with character recognition, especially in complex environments, leading to unreliable results and the need for extensive testing to adjust parameters.

Innovation Solution

A method that prioritizes the speed limit displayed on signs, using a navigation system and image processing system, where if no sign is detected within a threshold distance, it checks if the road type has changed, and if not, maintains the previous speed limit, otherwise using navigation data for new road types, with the only adjustable parameter being the distance threshold.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If navigation system data is used to determine speed limit, then the system can operate without image processing, but the speed limit information is often imprecise or absent

Engineering Contradiction:
Improvesystem complexityVSAvoidspeed limit accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines navigation system data with image processing system data to determine speed limit. The method integrates two different information sources (navigation database and visual recognition of speed limit signs) to overcome the limitations of each individual system, achieving both improved accuracy and reliability

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If image processing system is used to detect speed limit signs, then real-time detection is possible, but character recognition is unreliable especially when roads are lined with advertising signs

Engineering Contradiction:
Improvedetection reliabilityVSAvoidparameter adjustment complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary validation mechanism where the system compares results from both navigation data and image processing, and only accepts the image processing result when it meets confidence thresholds and contextual validation criteria. This intermediary step filters out unreliable character recognition results without requiring extensive parameter tuning

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If both methods are combined with weighted reliability, then more accurate speed limit determination is achieved, but the choice of parameters proves crucial and requires extensive testing

Engineering Contradiction:
Improvespeed limit accuracyVSAvoidsystem implementation ease
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent changes the approach from using multiple weighted parameters to using a single primary parameter (detection confidence threshold) and contextual parameters (road type, presence of obstacles). This simplifies the parameter set from multiple weighting factors to a manageable few, making the system easier to implement while maintaining accuracy

Inventive Principle:
Principle #35Parameter changes

4Loss of information

If character recognition algorithms are used on speed limit signs, then speed limit detection is possible, but the system is incapable of detecting the correct speed limit in complex situations like intersections and bifurcations

Engineering Contradiction:
Improveinformation completenessVSAvoidalgorithm complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent implements feedback mechanisms where the system continuously monitors detection confidence levels and contextual information (road type, vehicle position, presence of multiple signs). When confidence is low or contextual conditions suggest ambiguity (intersections, bifurcations), the system seeks additional validation from navigation data or adjusts detection parameters, creating a closed-loop system that adapts to complex situations

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3105752B1Method for determining a speed limit in force on a road taken by a motor vehicle
Publication Date: 2021.08.04 RENAULT SA

AI summary

The invention concerns a method for determining a speed limit in force on a road (1) taken by a motor vehicle (10). According to the invention, it involves carrying out the following steps: a) acquiring, at each speed limit sign (5) identified by camera, a first value of a parameter relative to the nature of the road taken, b) acquiring, when the distance travelled by the motor vehicle since the last speed limit panel was identified exceeds a predefined threshold, a second value of the parameter relative to the nature of the road taken, c) if the first and second values of said parameter are different, reading, in a navigation system, the speed limit associated with the road taken.