Urban 3D Modeling via Multi-Source Imagery Co-registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for creating high-fidelity, three-dimensional models of large-scale urban environments are laborious, time-consuming, and costly, limiting their industrial viability and inability to provide a genuine sense of realism.
Innovation Solution
A method involving the acquisition and co-registration of aerial and street-level imagery using stereo-pairs, terrestrial laser scans, and metadata to form a high-fidelity 3D model, divided into data layers with geometric and textual details, and integrated into a common coordinate system for accurate representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If current methodologies are used to produce precise and complete 3D-city models, then high-fidelity representation is achieved, but production time and costs become excessive
Solution Approach 1:
The patent segments the urban environment into discrete building units and processes them individually through automated photogrammetric workflows. Each building is modeled separately using its own set of photographs, allowing parallel processing and significantly improving overall production efficiency while maintaining high fidelity for each structure
Solution Approach 2:
The patent replaces manual, labor-intensive 3D modeling processes with automated photogrammetric systems that use computer algorithms to generate 3D models from 2D photographs. This substitution of mechanical/manual operations with automated computational processes dramatically reduces production time and costs while preserving modeling precision
2Manufacturing precision
If current methodologies are used to produce precise and complete 3D-city models, then high-fidelity representation is achieved, but production costs become excessive
Solution Approach 1:
The patent implements self-service through automated workflows where the photogrammetric system automatically processes photographs, extracts 3D geometry, and generates models without requiring manual intervention at each step. This automation reduces labor costs and makes high-fidelity 3D modeling economically viable for large-scale urban environments
Solution Approach 2:
The patent uses 2D photographs as copies of the real-world buildings to automatically generate 3D models. By using readily available photographic data instead of requiring expensive specialized scanning equipment or manual measurement processes, the system achieves high fidelity at lower production costs
3Ease of operation
If sketchy 3D models are used for urban environments, then navigation and viewing angle determination are enabled, but genuine sense of realism is lost
Solution Approach 1:
The patent performs preliminary actions by capturing comprehensive sets of photographs from multiple angles and elevations before generating the 3D models. This preliminary data collection ensures that sufficient visual information is available to create highly realistic models that maintain both navigational utility and genuine sense of place, rather than relying on crude geometric approximations
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
This approach significantly reduces production time and costs while providing a high-fidelity, realistic representation of urban environments, enabling efficient data collection and integration into industrially viable solutions.
Implementation Method 1
acquiring imagery of the urban environment including aerial imagery and street-level imagery
Implementation Method 2
a plurality of terrestrial laser scans
Implementation Method 3
terrestrial laser scans
Data Source
AI summary
A method, a system, and a program for high-fidelity three-dimensional modeling of a large-scale urban environment, performing the following steps:acquiring imagery of the urban environment, containing vertical aerial stereo-pairs, oblique aerial images; street-level imagery; and terrestrial laser scans,acquiring metadata pertaining to performance, spatial location and orientation of imaging sensors providing the imagery;identifying pixels representing ground control-points and tie-points in every instance of the imagery where the ground control-points and tie-points have been captured;co-registering the instances of the imagery using the ground control-points, the tie-points and the metadata, andreferencing the co-registered imagery to a common, standard coordinate system.The referenced co-registration obtained enables:extraction of ground coordinates for each pixel located in overlapping segments of the imagery, representing a 3D-point within the urban environment; andapplying data pre-processing and 3D modeling procedures;to create the high-fidelity 3D model of a large-scale urban environment.