Aerial Image Segmentation and DEM Projection for Site Volume Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing aerial images of construction sites are prone to errors due to incomplete site coverage, reliance on small data samples, and human errors in extrapolation, leading to inaccurate monitoring of progress and adherence to plans, especially for large sites.
Innovation Solution
A data-processing system that generates polygons from orthophoto maps and projects them onto digital elevation models to create reference surfaces, allowing for automated detection and precise estimation of object volumes without human intervention, using convolutional neural networks for segmentation and statistical processing of elevation coordinates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual surveying is performed by land surveyors, then measurement precision can be maintained at crucial points, but productivity decreases and coverage is limited to small samples
Solution Approach 1:
The patent replaces manual mechanical surveying with an automated optical system using aerial vehicles equipped with cameras. The system captures images of the entire construction site and uses computer-supported image processing to automatically identify objects and calculate volumes, eliminating the need for manual measurement while maintaining accuracy across the full site area.
Solution Approach 2:
The patent transitions from two-dimensional ground-level surveying to three-dimensional aerial imaging. By capturing images from above and processing them to extract depth information and calculate volumes, the system achieves comprehensive site coverage while maintaining measurement precision through automated analysis of the full three-dimensional space.
2Productivity
If aerial vehicles with cameras are used, then productivity and site coverage improve, but device complexity increases due to image processing requirements
Solution Approach 1:
The system performs self-service by automatically processing the captured images through computer-supported algorithms that identify construction objects, calculate their volumes, and generate reports without requiring complex manual intervention. The automated processing chain handles the complexity internally, allowing the system to maintain high productivity while managing the processing requirements efficiently.
3Loss of time
If only small samples are inspected by surveyors, then time is saved, but reliability decreases due to human and extrapolation errors
Solution Approach 1:
Instead of performing partial manual surveying at selected points, the system performs excessive action by capturing and analyzing images of the entire construction site. This comprehensive coverage eliminates the need for extrapolation and ensures that all areas are measured with consistent reliability, while the automated process keeps the time investment reasonable.
Data Source
AI summary
Disclosed is a system comprising a data-processing system. The data-processing system comprises a data-storage component, a segmentation component and a projection component. The data-storage component is configured for providing an input orthophoto map of an area and an input digital elevation model of the area. The segmentation component is configured for performing a segmentation step, the segmentation step comprises generating at least one or a plurality of polygon(s) based on the input orthophoto map. Each polygon approximates a part of the input orthophoto map. The projection component is configured for performing a projection step and the projection step comprises projecting the polygon(s) on the input digital elevation model of the area. The projection component is further configured for performing a reference surface generation step, the reference surface generation step comprising generating a reference surface for each of at least some of the polygon(s). Further, a corresponding method and a corresponding computer-program product are disclosed.