Vehicle Camera Positioning Using Regular Roadside Elements

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle detection systems using cameras and radars face limitations in determining precise spatial positions and kinematic parameters of objects due to resolution issues, especially with small target objects, and are prone to errors from optical adjustments and brightness variations.

Innovation Solution

Utilizing substantially identical elements regularly spaced in the vehicle's environment to estimate spatial positions and kinematic parameters by detecting and grouping these elements into classes, then projecting target objects relative to them for accurate positioning and parameter determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional cameras are used for detecting objects, then the device cost is reduced, but the measurement precision deteriorates because conventional cameras have insufficient resolution to provide usable images when the target object is very small

Engineering Contradiction:
Improvedistance and speed determination precisionVSAvoidimage quality
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The invention introduces a temporal dimension by analyzing the evolution of object characteristics across multiple images captured over time. Instead of relying solely on spatial resolution of a single image, the system tracks how object dimensions, position, and other characteristics change across a sequence of images, enabling precise measurement even when individual images have low resolution

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

Solution Approach 2:

The system performs preliminary detection and tracking of object characteristics across multiple frames before making a final determination. By accumulating data from successive images and tracking object evolution, the system prepares sufficient information in advance to accurately determine distance and speed parameters even with conventional camera resolution

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If radar is used for detecting objects, then the measurement precision is improved, but the range is limited to 250 meters which is too short to prevent dangers such as risky overtaking maneuver

Engineering Contradiction:
Improvedistance and speed determination precisionVSAvoiddetection range
Core Design Contradiction:
Measurement precisionVSLength of stationary object

Solution Approach 1:

The invention replaces the radar-based detection system with a camera-based optical system. Cameras have no inherent range limitation like radar's 250-meter constraint, allowing detection of objects at much greater distances. The system compensates for lower per-frame resolution by using temporal analysis across multiple images to achieve the necessary measurement precision

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If homography-based computing is used to determine object position, then the device complexity is reduced, but the measurement precision deteriorates because the accuracy depends on camera quality which may be insufficient

Engineering Contradiction:
Improvecomputing unit complexityVSAvoidobject position accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system continuously captures and analyzes a sequence of images over time, tracking the evolution of object characteristics across multiple frames. This continuous observation allows the system to accumulate measurement data and improve accuracy through temporal analysis, compensating for the simplicity of the homography-based computing approach and camera resolution limitations

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3394571B1Method and device for determining spatial positions and kinematic parameters of objects in the environment of a vehicle
Publication Date: 2025.07.30 RENAULT SA
  • EP3394571B1 patent drawingFigure 1
  • EP3394571B1 patent drawingFigure 2~3
  • EP3394571B1 patent drawingFigure 4

AI summary

The invention relates to a method for determining at least one spatial position or kinematic position, such as the trajectory, speed or acceleration, of at least one target object in the environment of a vehicle, said vehicle being provided with at least one camera for capturing images of the environment of said vehicle, said method comprising a step of capturing at least one image of the environment of the vehicle. According to the invention, the method also includes the following steps: determining the spatial distribution of at least three substantially identical elements with regular separation, and determining at least one target object contained in said at least one image; and, determining at least one spatial position or a kinematic parameter of said target object from said spatial distribution of at least three substantially identical elements with regular separation.