3D Point Cloud Volume Estimation Using Reference Plane Binning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional machine vision techniques face inefficiencies when processing massive 3D point clouds due to the lack of spatial relationship information, leading to complex and time-consuming volume computations, especially when surfaces are partially or wholly missing.
Innovation Solution
Utilizing a reference shape, such as a base plane, to compute volume by configuring a 2D grid of bins and determining the number and height of 3D points within each bin, allowing for quick and approximate volume estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional machine vision techniques process 3D point clouds directly, then volume computation can be performed, but the processing is complex and time-consuming due to the massive number of 3D points and lack of spatial relationship information
Solution Approach 1:
The patent segments the 3D point cloud by projecting points onto a 2D grid plane and organizing them into bins. This segmentation transforms the complex 3D processing task into simpler 2D bin-based processing, where points within each bin can be processed independently and efficiently, significantly reducing overall processing time while maintaining volume computation accuracy.
Solution Approach 2:
The patent introduces a 2D grid plane as an intermediary structure between the raw 3D point cloud and the volume computation process. This intermediary organizes 3D points into 2D bins with spatial relationships, serving as a mediator that simplifies the computation while preserving the necessary geometric information for accurate volume determination.
2Productivity
If conventional techniques process 3D point clouds without additional data structures, then processing resources are reduced, but the complexity of volume computation increases significantly
Solution Approach 1:
The patent transitions from direct 3D point cloud processing to a 2D grid-based representation by projecting 3D points onto a 2D plane. This dimensionality reduction creates an intermediate 2D structure that is easier to process, enabling faster volume computation while the added grid structure actually simplifies rather than complicates the overall processing architecture.
3Ease of manufacture
If 3D point clouds are used without surface normal information or relationship data, then data acquisition is simpler, but machine vision tasks become more complicated and time-consuming
Solution Approach 1:
The patent performs preliminary organization of 3D points by projecting them onto a 2D grid and assigning them to bins before the actual volume computation. This preliminary action pre-establishes spatial relationships and organizes the data structure, making subsequent processing operations simpler and more efficient without requiring complex surface normal calculations.
Data Source
AI summary
The techniques described herein relate to methods, apparatus, and computer readable media configured to determine an estimated volume of an object captured by a three-dimensional (3D) point cloud. A 3D point cloud comprising a plurality of 3D points and a reference plane in spatial relation to the 3D point cloud is received. A 2D grid of bins is configured along the reference plane, wherein each bin of the 2D grid comprises a length and width that extends along the reference plane. For each bin of the 2D grid, a number of 3D points in the bin and a height of the bin from the reference plane is determined. An estimated volume of an object captured by the 3D point cloud based on the calculated number of 3D points in each bin and the height of each bin.