Automated 2D Floor Plan Generation from 3D Voxels

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for generating 2D floor plans require human intervention and are time-consuming and costly, as they rely on expensive 3D scanning systems and manual extraction of data, resulting in outdated floor plans for most buildings, houses, and apartments.

Innovation Solution

A system that uses a mobile device with a depth camera to perform 3D scanning and generate a 2D floor plan by projecting voxels onto a 2D grid, extracting features like walls, free space, and furniture, and iteratively selecting primitives to minimize a cost function, thereby automating the generation of a 2D floor plan.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional 3D scanning systems with detectors on tripod are used, then measurement precision is improved, but device complexity and loss of time increase

Engineering Contradiction:

Improve3D geometry scanning accuracyVSAvoidscanning time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical tripod-based detector system with a mobile computing device that combines camera and processor. The mobile device captures 2D images and uses computational algorithms to generate 3D floor plans, eliminating the need for physical tripod positioning and manual measurement processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a digital 3D copy of the physical space by processing 2D images through computational algorithms. The generated floor plan is a virtual representation that replicates the spatial relationships and dimensions of the actual environment without requiring physical measurement tools.

Inventive Principle:

Principle #26Copying

2Measurement precision

If conventional 3D scanning systems are used, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improve3D geometry scanning accuracyVSAvoidscanning system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The mobile computing device performs multiple functions: capturing 2D images, processing images through algorithms, generating 3D floor plans, and providing user interface interactions. This single device replaces the specialized tripod-mounted detector system, making the technology accessible through a universal platform.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Manufacturing precision

If manual extraction of 2D floor plan from 3D geometry is performed, then manufacturing precision is improved, but loss of time increases

Engineering Contradiction:

Improve2D floor plan accuracyVSAvoidextraction time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces manual drafting processes with automated computational algorithms. The system processes 2D images and automatically generates accurate 3D floor plans through image processing and geometric reconstruction algorithms, eliminating the need for manual measurement and drawing operations.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically processing captured images and generating floor plans without human intervention. The computational algorithms autonomously extract spatial information, calculate dimensions, and produce the final 3D representation, freeing users from manual extraction tasks.

Inventive Principle:

Principle #25Self-service

4Device complexity

If mobile 3D scanning with depth camera is used, then device complexity is reduced, but measurement precision worsens

Engineering Contradiction:

Improvescanning device simplicityVSAvoid3D geometry accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

Inventive Principle:

Principle #26Copying

Solution Approach 2:

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10572970B2Extracting 2D floor plan from 3D GRID representation of interior space

Publication Date: 2020.02.25 GOOGLE LLC

AI summary

An imaging camera and a depth camera are configured to perform a 3D scan of an interior space. A processor is configured to generate voxels in a three-dimensional (3D) grid based on the 3D scan. The voxels represent portions of the volume of the interior space. The processor is also configured to project the voxels onto tiles in a two-dimensional (2D) floor plan of the interior space. The processor is further configured to generate, based on the tiles, a 2D distance grid that represents features in the interior space. In some cases, the 2D distance grid is generated in real-time concurrently with performing the 3D scan of the interior space. The processor is further configured to generate, based on a 2D distance grid, a set of polygons representing elements of the floor plan in real-time. The processor is further configured to generate a simplified set of primitives representing the floor plan.