Virtual Landmark Registration for Mobile 3D Environment Scanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D scanning technologies face challenges in automatic registration of scans, requiring manual intervention and resulting in inefficiencies, such as incomplete scans and increased costs, especially in time-sensitive situations like crime or accident scene investigations, due to the need for manual alignment and potential access issues.
Innovation Solution
A mobile scanning platform equipped with both 3D and 2D scanners that can operate simultaneously while moving, using virtual landmarks to automatically correct scan positions and enhance mapping accuracy, allowing for semi-autonomous or autonomous operation and reducing the need for manual registration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual registration procedures are used to align multiple 3D scans, then registration accuracy can be improved, but the time required and operational complexity increase significantly
Solution Approach 1:
The system performs automatic self-registration by having the scanner identify and match features autonomously without manual intervention. The scanner captures images, automatically detects features across multiple scans, and aligns them through computational matching, enabling the system to register scans itself rather than requiring external manual processing.
Solution Approach 2:
The patent replaces manual mechanical registration operations with automated computational processes. Instead of operators physically aligning scans using manual procedures, the system uses image processing algorithms and computer vision to automatically detect features and compute transformations, substituting human-operated mechanical alignment with automated digital processing.
2Reliability
If multiple scans are performed to obtain complete coverage of an environment, then scanning completeness is improved, but the complexity of registering and aligning multiple scans increases
Solution Approach 1:
The scanner automatically performs feature detection and matching across multiple scans without requiring external intervention. The system independently identifies features in each scan, matches them across the dataset, and computes alignment transformations, enabling autonomous handling of multi-scan registration complexity.
Solution Approach 2:
The system transforms the complex multi-scan registration problem into a series of manageable feature-matching operations. By changing from direct point-cloud registration to feature-based image matching, the system simplifies the computational parameters and makes the registration process more tractable and automated.
3Measurement precision
If manual registration procedures are used, then registration accuracy can be maintained, but operational efficiency and productivity decrease
Solution Approach 1:
The system autonomously performs the complete registration workflow including feature detection, matching, and alignment computation. This self-service capability eliminates the need for operators to manually process scans, maintaining accuracy through automated algorithms while dramatically improving productivity by parallelizing processing and eliminating human bottlenecks.
Solution Approach 2:
The patent replaces manual registration operations with automated computational systems. Instead of operators performing sequential manual alignment tasks, the system uses computer vision and image processing to automatically register scans, substituting human labor with automated digital processes that maintain accuracy while improving throughput and efficiency.
4Productivity
If automatic registration is attempted without manual intervention, then productivity is improved, but registration reliability and accuracy may deteriorate
Solution Approach 1:
The system replaces manual registration operations with robust automated image processing algorithms. By using computer vision techniques for feature detection and matching, the system achieves reliable automatic registration that maintains accuracy comparable to manual methods while improving productivity through automation and parallel processing.
Solution Approach 2:
The scanner performs autonomous feature-based registration without manual intervention. The system independently detects features, matches them across scans, and computes alignments, achieving both high productivity through automation and reliable accuracy through sophisticated algorithms that mimic and enhance manual registration capabilities.
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 faster and more accurate 3D scanning with reduced manual intervention, improving data quality and reducing costs by allowing for continuous scanning and automatic registration of scan positions, even in complex environments.
Implementation Method 1
transmitting a beam of light onto the objects and collecting the reflected or scattered light to determine the distance, two-angles (i.e., an azimuth and a zenith angle), and optionally a gray-scale value
Implementation Method 2
A TOF laser scanner is a scanner in which the distance to a target point is determined based on the speed of light in air between the scanner and a target point
Implementation Method 3
The beam steering mechanism includes a first motor that steers the beam of light about a first axis by a first angle that is measured by a first angular encoder (or other angle transducer). The beam steering mechanism also includes a second motor that steers the beam of light about a second axis by a second angle that is measured by a second angular encoder (or other angle transducer)
Data Source
AI summary
Generating a three-dimensional (3D) map of an environment includes receiving, via a 3D-scanner that is mounted on a moveable platform, a 3D-scan of the environment while the moveable platform moves through the environment. The method further includes receiving via a two-dimensional (2D) scanner that is mounted on the moveable platform, a portion of a 2D-map of the environment, and receiving first coordinates of the scan position in the 2D-map. The method further includes associating the scan position with the portion of the 2D-map as a virtual landmark. In response to the movable platform being brought back at the virtual landmark, a displacement vector for the 2D-map is determined based on a difference between the first coordinates and a second coordinates that are determined for the scan position. A revised scan position is calculated based on the displacement vector, and the revised scan position is used to register the 3D-scan.