Physical Structure Detection Using LiDAR and Cadastre Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for optimizing physical systems are limited by fragmented and inaccurate data sources, leading to missed opportunities for improvement and inefficiencies in resource utilization, particularly in complex structures where homogeneity and legal requirements are critical.
Innovation Solution
A method utilizing n-dimensional point data, such as LIDAR and LoD models, combined with secondary data like cadastral information, and machine learning models, especially artificial neural networks, to predict and implement optimizations in physical systems, ensuring scalability, reliability, and adherence to external requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional surveying methods with mobile measuring equipment are used, then measurement data can be obtained, but the data is fragmented, limited to simplified parameters, and provides only rough insights into actual conditions
Solution Approach 1:
The patent combines multiple data sources (LIDAR point clouds, photogrammetry data, cadastre data, BIM models) into a unified multi-dimensional data structure. This integration merges fragmented measurement data with contextual information, transforming rough insights into comprehensive system understanding without requiring complex separate processing of each data type.
Solution Approach 2:
The patent transitions from traditional 2D cadastre data and simplified measurement parameters to multi-dimensional representations (3D point clouds, 4D spacetime data, n-dimensional feature spaces). This dimensional expansion captures complex structures and relationships that were previously invisible, enabling precise analysis of spatial systems.
2Quantity of substance
If LIDAR technology is used for measuring earth's surface and objects, then comprehensive spatial data is obtained, but the data remains as uninterpreted point clouds that are difficult to analyze and provide further insight
Solution Approach 1:
The patent introduces intermediate data structures and processing layers that bridge raw LIDAR point clouds and meaningful insights. These intermediaries include structured point cloud representations, integrated multi-source data models, and machine learning feature extractors that transform uninterpreted spatial data into actionable system knowledge.
Solution Approach 2:
The patent replaces manual interpretation and traditional analysis methods with automated machine learning models and AI algorithms. These computational systems automatically extract meaningful patterns, classify objects, and generate insights from point cloud data, eliminating the information loss that occurs during manual processing.
3Measurement precision
If point cloud data is analyzed in detail, then measurement data is available, but individual measurement errors (outliers) lead to incorrect conclusions and massive subsequent errors in automated data processing
Solution Approach 1:
The patent implements feedback mechanisms through iterative processing and validation steps. Machine learning models process data in multiple passes, with each iteration refining results and correcting errors. The system continuously validates measurements against multiple data sources and uses error detection feedback loops to identify and correct outliers before they propagate through the analysis.
Solution Approach 2:
The patent applies error correction and validation procedures in advance of final analysis. Data cleaning, outlier detection, and quality assurance steps are performed beforehand to cushion against the propagation of measurement errors. This preventive approach ensures that individual errors do not lead to massive subsequent errors in the automated processing pipeline.
4Loss of information
If diverse data sources are integrated for system optimization, then comprehensive insights are achieved, but data fragmentation and different formats make it difficult to gain insight into potential opportunities
Solution Approach 1:
The patent creates a universal data integration framework that handles multiple data types and formats through a common processing architecture. This multi-functional system can ingest LIDAR data, photogrammetry outputs, cadastre information, and BIM models, transforming them all into a unified representation that enables comprehensive system analysis without requiring separate processing pipelines for each data source.
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
Enables precise and flexible optimization of physical systems by integrating diverse data sources, reducing errors, and suggesting improvements that can be effectively implemented, while maintaining system homogeneity and legal compliance.
Implementation Method 1
An example of this technology is Light Detection and Ranging (LIDAR or LiDAR). For example, a LIDAR measurement can be carried out as grid-based laser scanning on board an aircraft by measuring the structures under the aircraft.
Data Source
AI summary
The present invention relates to a method for optimizing the use of volume and/or surface area in a generic physical system (for example development plans, logistics and storage systems, quantum computers, solid-state systems, electron gases, plasmas), comprising the following steps: identifying a physical system in an n-dimensional space, in particular three-dimensional space, identifying an (n−1)-dimensional space, in particular two-dimensional space, which is suitable for describing an (n−1)-dimensional projection of the physical system in the n-dimensional space, providing n-dimensional point data, in particular lidar data, and/or LoD data, providing secondary data comprising (n−1)-dimensional data, in particular polygon data, in particular a cadastre, identifying one or more subsystems in the physical system, in particular using the secondary data, in particular also by assigning secondary data to the subsystems, determining subsystem data of at least two subsystems that describe variables of the respective subsystem, in particular comprising the secondary data of the respective subsystem and the n-dimensional point data and/or LoD data in relation to the respective subsystem, in full or in part, selecting at least one subsystem, using a supervised-learning machine-learning model, in particular a trained artificial neural network and/or a linear regression, to predict properties of the selected subsystem on the basis of the secondary data of the selected subsystem and of the subsystem data of other, non-selected subsystems. The invention additionally relates to corresponding computers, computer programs, computer networks, data and computer-readable data media and relevant uses.