3D Façade Orthoimage Generation With Automated Object Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual process of generating orthoimages for three-dimensional surfaces, particularly façades, is tedious and error-prone, requiring extensive user input to define mapping areas and volumes, which is inefficient and prone to inaccuracies.
Innovation Solution
A computer-implemented method that automates the selection of mapping areas and contents using machine learning and neural networks to identify wanted and unwanted objects, allowing for fully or partially automated generation of orthoimages, including features like balconies, oriels, and excluding obstructions such as trees and other buildings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processes are used to define mapping areas and volumes, then user control and precision are improved, but productivity and efficiency deteriorate
Solution Approach 1:
The system performs preliminary automated classification of objects into wanted and unwanted categories before the user needs to define mapping areas. This pre-processing step prepares the data structure and object identification in advance, reducing the time required for manual mapping area definition while maintaining precision through subsequent user validation.
Solution Approach 2:
The patent introduces an automated object classification system as an intermediary between raw 3D data and manual mapping area definition. This intermediary automatically identifies and categorizes objects, providing a structured foundation that accelerates the mapping process without completely replacing user control, thus resolving the contradiction between automation speed and precision.
2Measurement precision
If manual processes are used to define mapping areas and volumes, then accuracy and control are improved, but ease of operation deteriorates
Solution Approach 1:
The system enables self-service by allowing the automated classification process to perform the labor-intensive task of identifying and categorizing objects without continuous user intervention. The computer automatically processes 3D data, identifies objects, and assigns them to wanted or unwanted categories, significantly reducing ease of operation degradation while maintaining accuracy through user review capabilities.
Solution Approach 2:
By performing preliminary automated object identification and classification before user interaction, the system prepares the mapping volume specification in advance. This pre-computation reduces the manual effort required from users while preserving accuracy, as users only need to review and validate rather than create classifications from scratch.
3Productivity
If automated methods are used to select mapping content, then productivity is improved, but reliability deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the automated classification results are presented to users for review, validation, and correction. This feedback loop allows the system to maintain high productivity through automated processing while ensuring reliability by enabling users to verify and adjust object classifications, creating a hybrid approach that leverages both automation speed and human judgment.
Solution Approach 2:
The system applies partial automation by automating the initial object classification process while leaving room for user intervention when needed. This partial action approach maintains productivity benefits of automation while preserving reliability through selective human oversight, particularly for complex or ambiguous cases that require expert judgment.
Data Source
AI summary
A computer-implemented method for generating an orthoimage of a 3D structure, the method comprising receiving structure data comprising object data related to wanted objects and unwanted objects, selecting, based on the structure data, a mapping area including at least a part of the 3D structure, selecting mapping content comprising one or more wanted objects, and generating an orthoimage showing the mapping content. Selecting the mapping content may include, at least partially automatically, specifying a 3D mapping volume enclosing the mapping area, wherein the selected mapping content comprises objects that are located in the mapping volume, and/or performing a segmentation of the surface data to identify wanted and/or unwanted objects.