Onboard Camera Calibration for Driving Support Start Time

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Vehicle control systems face delayed driving support due to insufficient detection accuracy during the calibration process of onboard cameras, which is necessary for image recognition and driving support systems.

Innovation Solution

An information processing apparatus that sequentially performs a first and second calibration process of an onboard camera, using different Regions Of Interest (ROI) based on the camera's mounting stage, allowing for earlier initiation of driving support by adjusting detection accuracy according to the completion statuses of these processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the driving support is suppressed until the completion of the calibration process, then the detection accuracy is improved, but the start time of the driving support is delayed

Engineering Contradiction:
Improvedetection accuracyVSAvoidstart time delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The calibration process is divided into two distinct stages: a first calibration process that provides sufficient accuracy for basic driving support, and a second calibration process that achieves higher accuracy. By segmenting the calibration into phases, the system can activate driving support after the first calibration completes, rather than waiting for the entire calibration process, thus reducing start time delay while maintaining adequate detection accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs partial calibration (first calibration process) that achieves sufficient but not maximum detection accuracy to enable driving support to start. This partial action approach allows the system to achieve 'enough' accuracy to begin driving support without completing the full calibration process, thereby reducing the time delay while accepting that maximum precision is achieved only after the second calibration process.

Inventive Principle:
Principle #16Partial or excessive action

2Device complexity

If a single calibration process is performed, then the device complexity is reduced, but the detection accuracy is insufficient for early driving support

Engineering Contradiction:
Improvecalibration process complexityVSAvoiddetection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The calibration process is segmented into two distinct calibration processes with different complexity levels and accuracy outcomes. The first calibration process is simpler and faster, providing sufficient accuracy for basic driving support. The second calibration process is more complex but achieves higher accuracy. This segmentation allows the system to manage complexity while achieving the required detection accuracy for driving support.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The calibration system is designed to be dynamic, adapting the level of calibration performed based on system needs. The controller can determine whether to perform only the first calibration process (simpler, faster) or both the first and second calibration processes (more complex, higher accuracy) based on whether early driving support activation is prioritized or maximum detection accuracy is prioritized.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20240062551A1Information processing apparatus
Publication Date: 2024.02.22 DENSO TEN LTD
  • US20240062551A1 patent drawing
  • US20240062551A1 patent drawing
  • US20240062551A1 patent drawing

AI summary

An information processing apparatus according to an embodiment includes a controller. The controller is configured to estimate an attitude of an onboard camera, sequentially perform a first calibration process and a second calibration process of the onboard camera, and change a detection accuracy of an image recognition process of a captured image captured by the onboard camera depending on completion statuses of the first calibration process and the second calibration process.