Ground Surface Damage Mapping from Orthomosaic and 3D Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing software systems struggle to accurately detect and analyze damage anomalies and obstructions in ground surfaces from digital images, leading to incomplete or inaccurate damage reports.

Innovation Solution

A computer vision system that performs high-resolution scans, generates orthomosaics and digital surface models, detects damage, and extracts geometric features from digital images, ultimately producing a detailed damage report.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing software systems process aerial images, then image processing can be performed, but accurate detection of damage and anomalies cannot be achieved

Engineering Contradiction:
Improvedamage detection accuracyVSAvoiddamage report completeness
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system segments the image processing task into multiple specialized modules: orthomosaic generation for geometric correction, digital surface model creation for 3D reconstruction, damage detection for anomaly identification, and geometric extraction for feature measurement. Each module handles a specific aspect of analysis, allowing comprehensive and accurate damage assessment that overcomes the limitations of single-function systems.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from 2D image processing to 3D spatial analysis by generating digital surface models and orthomosaics that preserve geometric relationships. This dimensional transformation enables accurate measurement of damage features in three-dimensional space, improving both detection accuracy and report completeness compared to traditional 2D analysis.

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

2Measurement precision

If high resolution scanning is performed, then detection accuracy improves, but processing time and computational resources increase

Engineering Contradiction:
Improveground surface condition detection accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The processing workflow is divided into independent sequential modules that can be optimized individually: first generating orthomosaics from multiple images, then creating digital surface models, followed by damage detection and geometric extraction. This segmentation allows each stage to operate at optimal performance without unnecessarily processing the entire high-resolution dataset, reducing overall processing time while maintaining accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies damage detection algorithms selectively to regions identified as potentially damaged through preliminary analysis, rather than uniformly processing all high-resolution image data. This partial action approach maintains high detection accuracy for critical areas while significantly reducing computational resources and processing time for the complete dataset.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3856571B1Computer vision systems and methods for ground surface condition detection and extraction from digital images
Publication Date: 2026.02.25 INSURANCE SERVICES OFFICE INC
  • EP3856571B1 patent drawingFigure 1
  • EP3856571B1 patent drawingFigure 2
  • EP3856571B1 patent drawingFigure 3~4

AI summary

A system for detecting and extracting a ground surface condition from an image comprising a memory and a processor in communication with the memory. The processor performs a high resolution scan of at least one input image and generates an orthomosaic model and a digital surface model based on the performed high resolution scan. The processor generates an image tile based on the generated models and determines a label indicative of a probability of a presence of a ground surface condition for each pixel of the generated image tile via a computer vision model. The processor generates a label tensor for the at least one input image based on the determined labels and extracts a two- dimensional geospatial representation of a detected ground surface condition based on the generated label tensor. The processor generates a report indicative of damage associated with the detected ground surface condition based on the extracted two-dimensional geospatial representation.