Dual-Offset Camera Distance Evaluation for Vehicle Obstacle Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle obstacle detection systems, particularly those using single or dual cameras for stereoscopic calculations, suffer from precision errors due to camera positioning variability and temperature fluctuations, leading to inaccurate distance measurements, especially when detecting pedestrians or objects of varying heights.

Innovation Solution

Implementing a method that uses at least two cameras with parallel optical axes and offsets along both horizontal and vertical axes for stereoscopic calculations, combining distance evaluations from each offset to improve precision and incorporating calibration operations to account for camera position changes, with one camera positioned at a rear view mirror and the other at a front headlamp.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If a single camera is used for obstacle detection, then the cost is reduced, but the measurement precision of distance and object characteristics deteriorates

Engineering Contradiction:
ImprovecostVSAvoiddistance measurement precision
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent transitions from single-camera 2D imaging to dual-camera stereoscopic 3D imaging by adding a spatial dimension (baseline offset between cameras). This enables triangulation-based distance calculation, improving measurement precision while keeping costs lower than radar/lidar systems.

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

Solution Approach 2:

The patent introduces computational stereoscopic processing as an intermediary between the dual-camera input and distance measurement output. By implementing algorithms that calculate disparity between camera views, the system achieves precise distance measurement without requiring expensive dedicated hardware.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If two cameras are used for stereoscopic calculation, then the distance measurement precision is improved, but the device complexity increases

Engineering Contradiction:
Improvedistance measurement precisionVSAvoidcamera positioning complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the camera system multi-functional by using the same dual-camera setup for both stereoscopic distance measurement and monocular object height estimation. This universal approach improves measurement precision without proportionally increasing device complexity, as one hardware configuration serves multiple measurement purposes.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent segments the measurement task into two independent computational processes: horizontal baseline stereoscopic calculation for distance, and vertical offset analysis for height. This segmentation allows each function to be optimized independently, managing device complexity while maintaining high precision for both measurements.

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If cameras are positioned with offsets for stereoscopic calculation, then the distance evaluation precision is improved, but the sensitivity to positioning variations increases

Engineering Contradiction:
Improvedistance evaluation precisionVSAvoidrobustness to positioning variations
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent implements feedback by using the vertically-offset camera pair to verify and correct distance measurements from the horizontally-offset pair. The independent height-based distance estimation provides feedback that compensates for positioning errors in the primary stereoscopic calculation, improving reliability.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent cushions against positioning variations by designing the dual-offset camera system to provide redundant measurement paths. Before errors can significantly impact accuracy, the alternative measurement geometry (using vertical offset for height and distance) compensates, preventing error accumulation.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

4Measurement precision

If stereoscopic calculation is used for distance determination, then the distance measurement precision is improved, but the ability to determine object height deteriorates

Engineering Contradiction:
Improvedistance measurement precisionVSAvoidobject height information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent adds vertical dimension utilization by positioning cameras at different heights. This enables the system to extract both horizontal distance (from stereoscopic disparity) and vertical object height (from vertical offset geometry) simultaneously, preventing information loss while maintaining distance precision.

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

Solution Approach 2:

The patent makes the dual-camera system multi-functional by configuring it to perform both stereoscopic distance measurement and monocular height estimation. The same camera offsets that enable precise distance evaluation also provide the geometric basis for accurate height determination, eliminating the trade-off between these functions.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enhances the precision of distance measurements and allows for accurate determination of object height, reducing errors and improving the reliability of obstacle detection systems without the need for costly radar or lidar equipment.

Implementation Method 1

a first camera (201) and a second camera (202) having optical axes that are generally parallel to a first axis (Ox) of an orthogonal reference frame (103)

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentUS7987052B2Method for evaluation, by motor vehicle, of the characteristics of a front element
Publication Date: 2011.07.26 VALEO VISION SA
  • US7987052B2 patent drawing
  • US7987052B2 patent drawing
  • US7987052B2 patent drawing

AI summary

A method that utilizes at least a first camera and a second camera, which have optical axes that are parallel to a first axis of an orthogonal reference frame, the first and the second camera being positioned so as to have a first offset along a second axis and a second offset along a third axis of the orthogonal reference frame. The first offset is used to carry out a first stereoscopic calculation, and the second offset is used to carry out a second stereoscopic calculation, the distance sought finally being established by taking into consideration these two stereoscopic calculations.