3D Road Surface Display Using Single-Camera Pitch Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods face challenges in estimating depth information of a road surface using a single camera, which hinders the acquisition of 3D information necessary for autonomous driving and advanced driver-assistance systems.

Innovation Solution

A processor-implemented method that acquires driving images from a single camera, classifies line marks based on curvature changes, estimates pitch angles, and generates 3D information of the road surface, allowing for the display of 3D objects on the road surface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single camera is used to capture road surface images, then device complexity is reduced, but depth information estimation capability deteriorates

Engineering Contradiction:
Improvecamera system complexityVSAvoiddepth information estimation
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent transforms 2D image data into 3D road surface information by estimating pitch angles and generating three-dimensional road models. This dimensional transformation enables depth perception from single-camera 2D images, resolving the contradiction between using a simple single camera and achieving accurate depth estimation.

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

Solution Approach 2:

The patent changes parameters by estimating pitch angles of the road surface and using these parameters to generate 3D road models. By introducing pitch angle as a key parameter and transforming image coordinates into 3D coordinates using this parameter, the system achieves depth information estimation with a single camera.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If 3D road surface information is generated through complex processing, then measurement precision improves, but processing time increases

Engineering Contradiction:
Improve3D information accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the road surface into multiple regions and estimates pitch angles for each region separately. This segmentation allows parallel processing of different road areas, improving processing efficiency while maintaining accurate 3D information generation for each segment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-classifying line marks into groups based on curvature changes before pitch angle estimation. This pre-processing organizes the data structure, enabling more efficient subsequent processing and reducing overall computation time while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If line marks are classified into multiple groups based on curvature changes, then 3D information accuracy improves, but device complexity increases

Engineering Contradiction:
Improve3D information accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses curvature change as a parameter to classify line marks into different groups. By calculating and comparing curvature values at different positions, the system identifies transitions between straight sections and curved sections, enabling accurate pitch angle estimation for each group while maintaining manageable processing complexity.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3825904B1Method and apparatus with three-dimensional object display
Publication Date: 2024.01.24 SAMSUNG ELECTRONICS CO LTD
  • EP3825904B1 patent drawingFigure 1
  • EP3825904B1 patent drawingFigure 2
  • EP3825904B1 patent drawingFigure 3

AI summary

A method of displaying a three-dimensional (3D) object includes acquiring a driving image from a single camera, classifying line marks including a road surface into one or more groups based on a change in a curvature of a line of the road surface, estimating a pitch angle corresponding to an angle of inclination between the road surface and the single camera for each of the one or more groups, generating 3D information of the road surface, and displaying an 3D object visually overlaid on the road surface based on the 3D information of the road surface.