Traffic Light Detection via Position Deviation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting marked hazards and construction sites on roadways, particularly in urban and rural scenarios, lack the necessary accuracy and reliability, as they rely on generic object recognition and tracking techniques that fail to differentiate between stationary and mobile traffic light systems effectively.

Innovation Solution

A method utilizing a camera system or mono/stereo camera in conjunction with radar sensors to classify the environment scenario, create a reference model, and identify traffic light systems by comparing expected and actual positions, with additional features like power supply indicators and lane information enhancing detection reliability, and integrating digital map data for improved accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If generic object recognition and tracking techniques are used to detect marked hazards and construction sites, then the detection process is simple and fast, but the accuracy and reliability are insufficient

Engineering Contradiction:
Improvedetection reliabilityVSAvoiddetection system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The detection process is segmented into multiple stages: environment scenario classification, reference model determination, traffic light system detection, and position comparison. This segmentation allows each stage to focus on specific tasks, improving overall reliability while managing complexity through modular processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary classification of environment scenarios and determination of reference models before detecting traffic light systems. By preparing the reference framework in advance, the system can quickly and accurately compare detected objects against expected positions, enhancing detection reliability without proportionally increasing complexity

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the system only detects stationary traffic light systems at known intersections, then the detection algorithm is simple, but the system cannot identify mobile construction site traffic lights

Engineering Contradiction:
Improvedetection scopeVSAvoiddetection difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system transitions from static detection at fixed intersections to dynamic detection that adapts to mobile construction site traffic lights. By continuously comparing detected traffic light positions against the reference model and allowing for position deviations, the system can identify both stationary and mobile traffic light systems

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the detection parameters from fixed position matching to position deviation analysis. By measuring the deviation between detected and expected positions, the system can identify construction site traffic lights that operate outside standard intersection locations, expanding detection versatility

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If the system uses detailed object classification with construction site-specific features, then the detection accuracy improves, but the processing time increases

Engineering Contradiction:
Improveposition measurement precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies detailed classification only where necessary - specifically when a traffic light system is detected and needs position verification. The classification focuses on local features relevant to position determination rather than comprehensive object analysis, balancing precision with processing efficiency

Inventive Principle:
Principle #3Local quality

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach significantly enhances the detection of construction sites and hazardous points by accurately identifying traffic light systems, even when they deviate from expected positions, thereby improving safety and operational efficiency in various environments.

Implementation Method 1

a radar sensor, is characterized according to the invention in that a traffic light system is detected by means of the environment sensor

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentEP2912489B1Method and device for recognising marked hazard areas and/or construction areas in the region of carriageways
Publication Date: 2019.04.24 CONTI TEMIC MICROELECTRONIC GMBH
  • EP2912489B1 patent drawingFigure 1

AI summary

The invention relates to a method for recognising marked hazard areas and/or construction areas in the region of carriageways, in which method by means of at least one environment sensor the objects indicating hazard areas and/or construction areas are detected. According to the invention a traffic light system is detected by means of the environment sensor, the positional data of the traffic light system is determined, an environment scenario in respect of the environment structure is determined from the environment data detected by the environment sensor and is compared with a reference model of the environment scenario. If said reference model indicates no traffic light system or indicates a traffic light system having positional data differing from the positional data of the detected traffic light system, a conclusion is drawn about a traffic light system identifying a hazard and/or a construction area.