Adaptive 3D Cylindrical Projection for Wide-Angle Distortion Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle environment visualization systems using wide-angle lenses suffer from distortion, particularly with fisheye cameras, leading to inaccurate representation of object sizes and distances, which can obscure useful visual information and distract drivers, compromising safety.

Innovation Solution

The system employs an adaptive 3D cylindrical projection that dynamically changes based on detected objects' distances and a Panini projection optimized by detecting vanishing points and horizontal lines, combined with vertical compression to correct distortion, enabling wider panorama views with reduced distortion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of moving object

If a wide angle lens (120 degrees or higher) is used to capture the surrounding area, then the field of view is expanded, but distortion is introduced causing inaccurate representation of object sizes and distances

Engineering Contradiction:
Improvefield of viewVSAvoidobject size and distance accuracy
Core Design Contradiction:
Area of moving objectVSMeasurement precision

Solution Approach 1:

The patent applies parameter changes by dynamically adjusting the cylinder radius based on detected object distances. The system changes the projection parameters adaptively - when objects are detected at specific distances, the cylinder radius is modified to compensate for distortion, transforming the fixed projection model into a variable one that maintains accuracy across different viewing conditions

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent implements dynamics by making the cylinder radius adjustable rather than fixed. The system dynamically adapts the cylinder parameters based on real-time object detection and distance measurement, allowing the projection model to respond to changing scene conditions and maintain optimal distortion correction for varying fields of view

Inventive Principle:
Principle #15Dynamics

2Device complexity

If a rectilinear projection is used to correct fisheye distortion, then the projection is simplified, but distortion remains at the boundaries and worsens for wider fields of view

Engineering Contradiction:
Improveprojection complexityVSAvoidboundary distortion accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies spheroidality by using a cylindrical projection model instead of a simple rectilinear projection. The cylindrical geometry naturally handles the curvature effects of wide-angle lenses, providing a more accurate representation of the scene geometry while maintaining computational simplicity. The cylinder's curved surface accurately models the fisheye lens distortion characteristics

Inventive Principle:
Principle #14Spheroidality (Curvature)

3Area of moving object

If a Panini projection is used to project fisheye images, then the projection covers wide angles, but horizontal lines become curved introducing visual artifacts

Engineering Contradiction:
Improvepanorama coverageVSAvoidhorizontal line straightness
Core Design Contradiction:
Area of moving objectVSShape

Solution Approach 1:

The patent applies local quality by making the cylinder radius variable rather than uniform. Different regions of the projection have different cylinder radii based on detected object distances, allowing horizontal lines in specific regions to remain straight while maintaining wide-angle coverage. This localized adaptation preserves the straightness of horizontal lines where needed without sacrificing panorama coverage

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS20250022223A1Distortion correction for environment visualizations with wide angle views
Publication Date: 2025.01.16 NVIDIA CORP
  • US20250022223A1 patent drawing
  • US20250022223A1 patent drawing
  • US20250022223A1 patent drawing

AI summary

In various examples, a visualization of an environment may be generated using a Panini projection that is optimized based on detected scene content. For example, image data of an environment may be perspective projected (e.g., using a rectilinear projection) to generate a reference projection image, which may be analyzed to detect the presence of vanishing points and/or horizontal lines (e.g., in a central region). The image data of the environment may be projected using a Panini projection that is optimized based on distances to detected objects, the absence of a detected vanishing point, and/or the presence of a detected horizontal line to generate a Panini projection image. In some embodiments, vertical compression is applied to the Panini projection image to correct for distortion of horizontal lines (e.g., based on the presence of a detected horizontal line).