Terrain Topography Change Evaluation Using GPU Point Cloud Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods struggle to efficiently process large point clouds representing terrain topography, which are increasingly complex due to improved measurement resolution, leading to processing power requirements that are difficult to manage with traditional computer systems.
Innovation Solution
A method utilizing graphics processing units (GPUs) to divide point clouds into grid cells, determine point planes, measure plane offset distances, align point clouds, calculate normal directions, and identify corresponding points to generate a third point cloud representing topographical differences, leveraging parallel processing capabilities for efficient evaluation of terrain changes over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional computer systems are used to process large point clouds, then processing power requirements become difficult to manage, but the patent uses GPUs with parallel processing capabilities to efficiently evaluate terrain changes
Solution Approach 1:
The patent divides the large point cloud into multiple smaller point clouds using a grid-based segmentation approach. The terrain area is divided into grid cells, and points are distributed across these cells, allowing parallel processing of smaller subsets rather than handling the entire massive point cloud as a single unit. This segmentation enables efficient utilization of GPU parallel processing capabilities.
Solution Approach 2:
The patent introduces a spatial dimension by organizing points into a grid structure with cell indices. This grid-based organization adds spatial indexing dimensions to the processing approach, enabling efficient parallel access and processing of point cloud data across multiple GPU cores simultaneously.
2Measurement precision
If high resolution measurement systems are used to generate point clouds, then topographical detail is improved, but the point cloud size increases making processing more difficult
Solution Approach 1:
The patent segments the large high-resolution point cloud into multiple smaller point clouds based on grid cell divisions. Each smaller point cloud contains a subset of the original points, maintaining the high measurement precision of the original data while reducing the computational burden by processing smaller units in parallel.
Data Source
AI summary
Systems and methods for evaluating changes in terrain topography over time are provided. A first point cloud corresponds to the terrain topography during a first time period. A second point cloud corresponds to the terrain topography during a second time period. One or more processors collectively execute instructions to: for each point in the first point cloud, determine a point plane; align the first and second point clouds based on a plurality of plane offset distances; for each point in the aligned second point cloud, calculate a normal direction; for each point in the aligned second point cloud, identify one or more corresponding points in the aligned first point cloud; and generate a third point cloud representing topographical differences. The first point cloud can be divided into a plurality of grid cells and a plurality of graphics processing cores can execute parallel point processing based on the plurality of grid cells.