Lane Detection via Vehicle-to-Vehicle Communication

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing lane detection systems are significantly affected by unclear or blurred road markings, especially in adverse weather conditions, leading to inaccurate lane identification.

Innovation Solution

A lane detection method that utilizes vehicle-to-vehicle communication to calculate the lane position of a vehicle based on dynamic data, including GPS, velocity, and heading data from neighboring vehicles, with an anomaly removal process and clustering algorithm to determine the lane information, further utilizing lane width and digital maps for accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If image processing technology relying on road marks is used for lane detection, then the system structure is simple, but the detection accuracy deteriorates significantly in adverse weather conditions when road marks are unclear or blurred

Engineering Contradiction:
Improvesystem structureVSAvoidlane detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent introduces vehicle-to-vehicle communication as an intermediary mechanism to transfer trajectory data between vehicles. Instead of directly detecting road marks, the system uses communicated trajectory information from neighboring vehicles as a mediator to infer lane positions, thereby avoiding the limitations of direct image processing in adverse weather conditions

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transitions from two-dimensional image processing of road marks to three-dimensional spatial trajectory analysis by incorporating GPS coordinates, velocity vectors, and temporal information. This dimensional expansion allows the system to determine lane positions through spatial reasoning rather than relying on degraded visual features

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If vehicle-to-vehicle communication with multiple data processing steps is implemented, then the lane detection accuracy is improved, but the device complexity increases

Engineering Contradiction:
Improvelane detection accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary actions by having neighboring vehicles pre-calculate and transmit their trajectory data through vehicle-to-vehicle communication. This preliminary preparation of trajectory information eliminates the need for the receiving vehicle to perform complex real-time calculations, thereby reducing processing complexity while maintaining high detection accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by receiving and utilizing trajectory data from neighboring vehicles instead of performing independent lane detection. The receiving vehicle copies the trajectory information and applies clustering algorithms to determine its lane position, which is computationally simpler than direct image processing or independent sensor-based detection

Inventive Principle:
Principle #26Copying

Data Source

PatentUS10928524B2Lane detection
Publication Date: 2021.02.23 HARMAN INT IND INC
  • US10928524B2 patent drawing
  • US10928524B2 patent drawing
  • US10928524B2 patent drawing

AI summary

A lane detection method and a lane detection system mounted on a first vehicle are provided. The methods includes: calculating on which lane a first vehicle is located based on vehicle-to-vehicle data received by the first vehicle from at least one neighboring vehicle, where the neighboring vehicle means another vehicle located within a vehicle-to-vehicle communication range of the first vehicle. The system may include: a communication device for receiving vehicle-to-vehicle data from at least one neighboring vehicle, and a processing device for calculating on which lane the first vehicle is located based on the vehicle-to-vehicle data received by the communication device, where the neighboring vehicle means another vehicle located within a vehicle-to-vehicle communication range of the first vehicle. Lane detection may not rely on marks on roads which are inherently not clear or blur due to a bad weather.