Underground Structure Detection via Synthetic Radar and 3D Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing underground structure detection methods using radar technology are limited in accurately detecting components deeper in the ground, as they struggle to provide precise position and posture information of buried objects like water pipes and communication lines, and are not effective in integrating two-dimensional and three-dimensional data for comprehensive analysis.

Innovation Solution

An underground structure detection apparatus that synthesizes two-dimensional and three-dimensional data to correct position and posture information of underground components, utilizing a combination of radar data, camera images, and blueprint data to generate accurate three-dimensional models and classify components, thereby enhancing detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If only radar images are used for underground structure detection, then the detection process is simple, but the detection accuracy and ability to determine position and posture of deep components is limited

Engineering Contradiction:
Improvedetection accuracyVSAvoiddata integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple data sources including radar images, two-dimensional cross-sectional data, and three-dimensional underground structure data into synthetic data. This merging of different data types enables accurate determination of component positions and postures by leveraging the complementary strengths of each data source, resolving the contradiction between detection accuracy and system complexity.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent synthesizes two-dimensional data with three-dimensional data to create enhanced three-dimensional models. By transitioning from purely two-dimensional radar images to integrated three-dimensional representations, the system achieves superior detection accuracy for deep underground components while maintaining manageable complexity through automated synthesis processes.

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

2Loss of information

If three-dimensional models are generated from multiple radar images, then deep underground components can be visualized, but the position and posture information remains inaccurate

Engineering Contradiction:
Improveinformation completenessVSAvoidposition and posture accuracy
Core Design Contradiction:
Loss of informationVSMeasurement precision

Solution Approach 1:

The patent introduces two-dimensional cross-sectional data as an intermediary to bridge radar images and three-dimensional models. This intermediate data layer provides accurate positional references that correct the position and posture information in three-dimensional models, ensuring both information completeness and measurement precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system uses two-dimensional data to correct and refine the three-dimensional model information. By feeding back positional and postural corrections from the two-dimensional cross-sectional data to the three-dimensional model, the system maintains high accuracy in component location and orientation while preserving complete underground structure information.

Inventive Principle:
Principle #23Feedback

3Reliability

If manual classification of underground components is performed, then classification accuracy can be maintained, but labor and time consumption increases

Engineering Contradiction:
Improveclassification accuracyVSAvoiddetection efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements automated classification functionality that enables the system to classify underground components independently without requiring manual intervention. The classification algorithm processes the synthesized data and automatically identifies component types, maintaining high reliability through consistent application of classification criteria while dramatically improving productivity by eliminating manual labor.

Inventive Principle:
Principle #25Self-service

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

The apparatus enables accurate detection and classification of underground components, improving positional and postural accuracy and reducing labor through automated classification, while minimizing dimensional deviations and incorrect classifications.

Implementation Method 1

A technique for measuring an underground buried object by a radar from a road is disclosed

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

irradiates a radar from a mobile object such as a vehicle and explores under a road surface

Methodology Applied
Scientific EffectElectromagnetic wave propagation: Electromagnetic Induction

Data Source

PatentUS20230289490A1Underground structure detection apparatus and underground structure detection method
Publication Date: 2023.09.14 HITACHI LTD
  • US20230289490A1 patent drawing
  • US20230289490A1 patent drawing
  • US20230289490A1 patent drawing

AI summary

An underground structure detection apparatus detects information including position/posture information based on a plurality of pieces of two-dimensional data indicating a cross section of the ground and three-dimensional data indicating the underground structure. Synthetic data is obtained by synthesizing the two-dimensional data and the three-dimensional data, and position/posture information of a component is corrected based on an image from the two-dimensional data. When a determination is made in a transverse direction with respect to a road, and the image feature is included in continuous images by a threshold or more, it is determined as a transverse pipe, and when a determination is made in a longitudinal direction with respect to a road, and the image feature is included in continuous images by a threshold or less, it is determined as a longitudinal pipe, and the posture is corrected for each direction.