In-Vehicle Camera Calibration on Multi-Flat Road Surfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

High precision calibration of in-vehicle camera external parameters is challenging, especially when the road surface is not flat, as existing methods require pre-factory calculations that do not account for changes in vehicle posture due to passengers or cargo shifts during travel.

Innovation Solution

A calibration device and method that uses a camera mounted on a vehicle to extract characteristic points, track them, estimate a flat surface, calculate a calibration trajectory, and calibrate external camera parameters in real-time while traveling, allowing for accurate calibration even on multi-flat road surfaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If external parameters are calculated using a predetermined test pattern in the factory before shipment, then the calibration process is simplified and standardized, but the calibration precision deteriorates because vehicle posture changes during travel are not accounted for

Engineering Contradiction:
Improvecalibration process simplicityVSAvoidexternal parameter calibration precision
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system performs preliminary calibration in the factory using a test pattern to establish baseline external parameters, then performs additional calibration during actual travel to refine these parameters and account for vehicle posture changes

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from characteristic point tracking during travel to continuously refine and update external parameters, correcting deviations caused by vehicle posture changes that were not present during factory calibration

Inventive Principle:
Principle #23Feedback

2Measurement precision

If calibration is performed while the vehicle is traveling on the road, then the calibration precision is improved by accounting for actual vehicle posture, but the calibration complexity increases due to dynamic environmental factors

Engineering Contradiction:
Improveexternal parameter calibration precisionVSAvoidcalibration system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses the vehicle's own camera and existing travel data to perform self-calibration, eliminating the need for external calibration equipment or specialized calibration vehicles while achieving high precision through characteristic point tracking of road surfaces

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If characteristic points are tracked on non-flat road surfaces, then more road conditions can be covered, but the calibration accuracy deteriorates due to surface irregularities

Engineering Contradiction:
Improveroad surface adaptabilityVSAvoidcalibration accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system identifies and selects only the flat road surface portions from the captured images for characteristic point tracking, excluding irregular portions that would compromise calibration accuracy, thus maintaining high precision while still adapting to various road conditions

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS11636624B2Calibration device and calibration method
Publication Date: 2023.04.25 FAURECIA CLARION ELECTRONICS CO LTD
  • US11636624B2 patent drawing
  • US11636624B2 patent drawing
  • US11636624B2 patent drawing

AI summary

High precision calibration of external parameters is possible even when the surrounding road surface is configured from a plurality of flat surfaces. Specifically, provided is a calibration device comprising a camera to be mounted on a vehicle traveling on a road surface; a characteristic point extraction unit which extracts characteristic points from a captured image obtained by being captured with the camera; a tracking unit which tracks the characteristic points extracted with the characteristic point extraction unit; a storage unit which stores a trajectory of the characteristic points obtained by tracking the characteristic points; a road surface estimation unit which estimates a flat surface on which the vehicle is traveling by using the trajectory of the characteristic points; a calculation unit which calculates a calibration trajectory, which is a trajectory of the characteristic points, for use in calibration based on the estimated flat surface; and an external parameter estimation unit which executes calibration of an external parameter of the camera by using the calibration trajectory.