3D Information Labeling via 2D Projection Substitution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for obtaining three-dimensional information of objects on a road, such as using lidar or manual adjustment of projections, are costly, labor-intensive, and inefficient, with low quality guarantees.

Innovation Solution

A method and apparatus that process three-dimensional information by obtaining target image data, determining two-dimensional projection information, and using trained models to derive three-dimensional information, thereby avoiding the need for lidar and improving efficiency and quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If lidar is used for three-dimensional information labeling, then measurement precision is improved, but device complexity and cost increase

Engineering Contradiction:
Improvethree-dimensional information labeling qualityVSAvoidlidar installation and hardware support
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses two-dimensional projection information as a copy or representation of the three-dimensional object, which can then be processed to obtain three-dimensional information. This copying approach replaces the need for expensive lidar hardware while maintaining the ability to obtain accurate three-dimensional measurements through computational methods.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical lidar system with a computational approach that processes two-dimensional image data. Instead of using physical laser ranging equipment, the system uses image processing algorithms and projection geometry to derive three-dimensional information, substituting a mechanical system with an information-processing system.

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

2Device complexity

If manual adjustment of projection is used for three-dimensional information labeling, then device complexity is reduced, but productivity and measurement precision deteriorate

Engineering Contradiction:
Improvehardware requirementsVSAvoidlabeling efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system enables self-service by automatically obtaining three-dimensional information from two-dimensional projection data without requiring manual adjustment. The computational processing automatically performs the labeling task that would otherwise require human operators to manually adjust projections, achieving both reduced device complexity and improved productivity.

Inventive Principle:
Principle #25Self-service

3Device complexity

If manual adjustment of projection is used for three-dimensional information labeling, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvehardware requirementsVSAvoidlabeling quality
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces manual mechanical adjustment with an automated computational system that processes two-dimensional projection information. This substitution maintains low device complexity while dramatically improving measurement precision through algorithmic processing that can accurately derive three-dimensional coordinates from two-dimensional data without human error.

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

4Measurement precision

If lidar is used for three-dimensional information labeling, then measurement precision is improved, but loss of time increases due to manpower requirements

Engineering Contradiction:
Improvethree-dimensional information labeling qualityVSAvoidmanpower demand time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically processing two-dimensional image data to obtain three-dimensional information without requiring human operators. This automation eliminates the time loss associated with manual data processing and labeling while maintaining high measurement precision through computational methods.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent enables continuous processing of three-dimensional information by automating the entire workflow from image acquisition to three-dimensional labeling. Unlike manual methods that require intermittent human intervention, the automated system can continuously process data without interruption, eliminating time loss while maintaining precision.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3985575B1Three-dimensional information processing method and apparatus
Publication Date: 2024.09.11 GUANGZHOU XIAOPENG MOTORS TECH CO LTD
  • EP3985575B1 patent drawingFigure 1~2
  • EP3985575B1 patent drawingFigure 3
  • EP3985575B1 patent drawingFigure 4

AI summary

Embodiments of the present disclosure provide a method and an apparatus for processing three-dimensional information. The method includes: obtaining target image data for a target three-dimensional object; determining target two-dimensional projection information of the target three-dimensional object from the target image data; and obtaining target three-dimensional information of the target three-dimensional object based on the target two-dimensional projection information. According to the embodiments of the present disclosure, three-dimensional information labeling is optimized. Also, obtaining three-dimensional information of a three-dimensional object based on two-dimensional information of the three-dimensional object avoids the dependence on a lidar and improves the efficiency and quality of the three-dimensional information labeling.