3D Polygon Projection onto Occluded Ground Surfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional 3D image projection methods fail to accurately project polygons onto invisible or occluded ground surfaces, complicating object detection in real-world scenarios.

Innovation Solution

A method involving 2D image data acquisition, 3D polygon detection, and ray casting to establish correspondence between 2D pixel coordinates and 3D surface coordinates, enabling precise projection of 3D polygons onto a segmented ground segment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If 2D monocular cameras are used for cost-effectiveness, then device cost is reduced, but 3D perspective understanding capability deteriorates

Engineering Contradiction:
Improvedevice costVSAvoid3D perspective understanding capability
Core Design Contradiction:
Ease of manufactureVSLoss of information

Solution Approach 1:

The patent projects 2D image data onto a 3D surface model, transforming 2D visual information into 3D spatial representation. This allows 2D monocular cameras to achieve 3D perspective understanding by mapping detected polygons and correspondence information onto the 3D ground surface model, effectively adding a dimensional transformation to compensate for the camera's inherent 2D limitation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Ease of operation

If conventional polygon projection methods are used on visible ground, then projection simplicity is maintained, but projection accuracy deteriorates in occluded conditions

Engineering Contradiction:
Improveprojection simplicityVSAvoidprojection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent performs preliminary segmentation of the 3D surface model to extract the ground surface model before projection. By pre-processing the 3D model to separate ground from non-ground elements, the system prepares the appropriate projection surface in advance, enabling accurate projection even when the ground is occluded in the 2D image, as the 3D model contains complete spatial information regardless of occlusion.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a 3D surface model as an intermediary between the 2D image and the ground projection. Instead of projecting directly from 2D to ground, the system uses the 3D surface model as a mediator that contains complete spatial information, allowing accurate polygon projection by establishing correspondence between 2D pixel coordinates and 3D surface coordinates through ray casting.

Inventive Principle:
Principle #24Intermediary (Mediator)

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 accurate 3D polygon projection even in occluded or invisible ground conditions, enhancing object detection and visualization in real-world scenarios.

Implementation Method 1

determining, by applying a ray casting operation on the 2D images and the ground segment of the 3D surface model, correspondence information between 2D pixel coordinates in the 2D images and 3D surface coordinates of the ground segment

Methodology Applied
Scientific EffectRay casting:

Data Source

PatentEP4614437A1Dynamic multi-dimensional media content projection
Publication Date: 2025.09.10 FUJITSU LTD
  • EP4614437A1 patent drawingFigure 1
  • EP4614437A1 patent drawingFigure 2
  • EP4614437A1 patent drawingFigure 3A

AI summary

In an embodiment, dynamic multi-dimensional media content is projected. Image data including 2D images depicting view of real-world is acquired. 3D polygons are detected corresponding to objects on a ground of the 2D images. 3D surface model is segmented into 3D segments including ground segments and non-ground segments. The ground segment of the 3D surface model is extracted by removing the one or more non-ground segments from the plurality of 3D segments. Corresponding information between 2D pixel coordinates in the 2D images and 3D surface coordinates of the ground segments is determined by applying a ray casting operation on the 2D images and the ground segment of the 3D surface model. The 3D polygons are projected onto the 3D surface model based on the correspondence information.