Vertical Image Stitching for Undistorted Vehicle Side Views

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Vehicle operators face difficulty in efficiently analyzing images from multiple cameras in camera monitor systems due to overlapping fields of view and optical angles, leading to image distortion and a fragmented view of the vehicle's surroundings.

Innovation Solution

A method and system for vertical image stitching that involves obtaining images from cameras with different overlapping fields of view and optical angles, applying perspective transformations and distortion corrections, and combining these images to form a cohesive, undistorted view.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of moving object

If multiple cameras with different fields of view and optical angles are used to provide a comprehensive view, then the field of view coverage is improved, but image distortion and fragmentation increase

Engineering Contradiction:
Improvefield of view coverageVSAvoidimage distortion and fragmentation
Core Design Contradiction:
Area of moving objectVSObject-generated harmful factors

Solution Approach 1:

The patent merges multiple images from different cameras with overlapping fields of view into a single stitched image. The image processing system combines the plurality of images by aligning overlapping regions and blending them seamlessly, creating a unified composite image that eliminates fragmentation while maintaining comprehensive field of view coverage.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent applies parameter transformations to correct image distortion. The system modifies image parameters including perspective transformation, distortion correction, and geometric warping to compensate for the different optical angles and lens characteristics of multiple cameras, thereby eliminating image distortion in the stitched output.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If images from multiple cameras are displayed separately, then image quality and detail are maintained, but operator efficiency in analyzing the environment decreases

Engineering Contradiction:
Improveimage quality and detailVSAvoidoperator efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent combines multiple separate camera images into a single stitched image that preserves the detailed quality of individual images while presenting a unified view. This merging process maintains the high resolution and detail from each camera source while eliminating the need for operators to switch between multiple displays, thereby improving analysis efficiency.

Inventive Principle:
Principle #5Merging (Combining)

3Area of moving object

If additional cameras are added to provide a larger field of view, then the coverage area is improved, but system complexity and cost increase

Engineering Contradiction:
Improvecoverage areaVSAvoidsystem complexity
Core Design Contradiction:
Area of moving objectVSDevice complexity

Solution Approach 1:

The patent makes existing cameras perform multiple functions by utilizing their overlapping fields of view for image stitching rather than requiring dedicated cameras for specific zones. The system processes and combines images from standard cameras to achieve panoramic coverage, eliminating the need for specialized additional cameras and reducing system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4675547A1Method and system for vertical image stitching
Publication Date: 2026.01.07 STONERIDGE ELECTRONICS
  • EP4675547A1 patent drawingFigure 1
  • EP4675547A1 patent drawingFigure 2
  • EP4675547A1 patent drawingFigure 3

AI summary

A method for a camera monitor system (CMS) includes obtaining a first image from a first camera and a second image from a second camera. The first image and second image depict a side of a commercial vehicle and its surrounding environment. The first camera and the second camera have different, overlapping fields of view, and have different respective optical axes that intersect a ground plane at different respective optical angles. The method also includes performing a perspective transformation on at least one of the first image and second image to obtain an updated image set, such that at least one of the first image and second image are updated in the updated image set, and vertically stitching the images of the updated image set together to form a combined image. A camera monitor system (CMS) is also disclosed.