Traffic Signal Recognition Using Stop-Line-Based Detection Areas

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing traffic signal recognition methods face delays in alarm generation when intersection intervals are close and incur high computational loads when detecting multiple traffic signals simultaneously.

Innovation Solution

A traffic signal recognition device that includes an imaging unit, in-vehicle sensor, map information acquisition unit, and controller, which sets detection areas based on the vehicle's position and deceleration capabilities to selectively focus on critical traffic signals, reducing computational load by only processing images for signals where the vehicle cannot stop, even at close intervals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the display state of traffic signals is detected sequentially at each intersection, then the system can identify traffic signals, but the alarm generation is delayed when the intervals between intersections are relatively close

Engineering Contradiction:
Improvetraffic signal detection accuracyVSAvoidalarm generation delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by predicting the vehicle's stop position based on current speed and deceleration characteristics, and pre-identifies traffic signals that will be relevant before the vehicle actually reaches them. This allows the system to prepare alarm conditions in advance, eliminating delays when intersections are close together.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts which traffic signals are monitored based on real-time vehicle speed, deceleration rate, and distance to intersections. Instead of a fixed monitoring approach, the system adapts the detection scope to match the vehicle's actual stopping behavior, ensuring timely alarm generation for critical signals while ignoring those that won't affect the current stop decision.

Inventive Principle:
Principle #15Dynamics

2Loss of information

If the display of multiple traffic signals is simultaneously determined, then comprehensive traffic signal information is obtained, but the computational load becomes large

Engineering Contradiction:
Improvetraffic signal information completenessVSAvoidcomputational load
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system extracts and processes only the subset of traffic signals that are relevant to the vehicle's current stopping behavior. By calculating the predicted stop position and identifying only those traffic signals within the relevant range, the system avoids the computational burden of processing all detected traffic signals while still obtaining complete information about signals that matter.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies different processing levels to different traffic signals based on their relevance. Traffic signals near the predicted stop position receive full analysis, while those farther away are either ignored or given minimal processing. This localized quality approach ensures comprehensive information for critical signals without uniformly high computational cost across all signals.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If detection areas are set at positions of all detected traffic lights, then all traffic signals are monitored, but the computational load increases when multiple traffic signals are present

Engineering Contradiction:
Improvetraffic signal detection coverageVSAvoidcomputational load
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts only the necessary detection areas corresponding to traffic signals that will actually influence the vehicle's stopping behavior. By using the predicted stop position as a reference, the system identifies and processes only those traffic signals within the relevant detection range, eliminating unnecessary computational load from monitoring signals that won't affect the current stop decision.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4060643B1Traffic signal recognition method and traffic signal recognition device
Publication Date: 2024.02.28 NISSAN MOTOR CO LTD
  • EP4060643B1 patent drawingFigure 1
  • EP4060643B1 patent drawingFigure 2
  • EP4060643B1 patent drawingFigure 3

AI summary

A traffic signal recognition method and a traffic signal recognition device estimate whether or not a vehicle can be decelerated at a predetermined deceleration acceleration and can stop before a stop line based on a position of the stop line corresponding to a traffic signal located in a traveling direction of the vehicle, select the traffic signal corresponding to the stop line as a target traffic signal in a case where it is estimated that the vehicle cannot stop before the stop line, set detection area corresponding to the target traffic signal on an image obtained by capturing the traveling direction of the vehicle, and determine a display state of the target traffic signal by executing image processing on the detection area.