Vehicle Surround Image Stitching With Benchmark Image Enhancement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The limited field of view and distortion of camera images, especially at distant angles, lead to blurry and distorted images in vehicle surrounding views, and stitching these images results in ghosting artifacts, compromising the accuracy of the panoramic view.

Innovation Solution

A method involving multiple vehicle-mounted cameras capturing images from different angles, comparing them with external images from devices like smart poles, selecting high-quality benchmark images, enhancing features like brightness and sharpness, and stitching these enhanced images to create a clear panoramic view.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If multiple cameras are used to capture surrounding images, then the field of view is expanded, but image distortion and blurring worsen at distant angles

Engineering Contradiction:
Improvefield of viewVSAvoidimage quality
Core Design Contradiction:
Area of stationary objectVSManufacturing precision

Solution Approach 1:

The patent applies preliminary action by performing enhancement processing on images before they are stitched together. The system pre-processes individual camera images to correct distortion and improve quality, then combines them. This prevents the accumulation of errors that would occur if enhancement were done after stitching, thereby resolving the contradiction between expanded field of view and maintained image quality.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies local quality by selectively enhancing different regions of images based on their specific characteristics. The enhancement processing adapts to local image properties, applying different correction strengths to different areas. This allows distant angle images to receive more aggressive correction while preserving quality in already-good regions, resolving the contradiction between wide coverage and uniform image quality.

Inventive Principle:
Principle #3Local quality

2Area of stationary object

If images are stitched together to form panoramic view, then the surrounding coverage is improved, but ghosting artifacts appear

Engineering Contradiction:
Improvesurrounding coverageVSAvoidimage accuracy
Core Design Contradiction:
Area of stationary objectVSReliability

Solution Approach 1:

The patent performs enhancement processing on individual images before stitching, which preliminarily corrects distortion and aligns features. This pre-alignment reduces mismatches during the stitching process, thereby minimizing ghosting artifacts while maintaining comprehensive surrounding coverage.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses evaluation information from multiple images to guide the enhancement processing. By comparing features across images and using this feedback to adjust enhancement parameters, the system optimizes the stitching process to minimize ghosting while maximizing coverage, thereby resolving the contradiction between surrounding coverage and image accuracy.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20250336038A1Method, device and non-transitory computer-readable storage medium for enhancing vehicle surrounding images
Publication Date: 2025.10.30 NANNING FUGUI PRECISION IND CO LTD
  • US20250336038A1 patent drawing
  • US20250336038A1 patent drawing
  • US20250336038A1 patent drawing

AI summary

A method, a device and a non-transitory computer readable storage medium for enhancing vehicle surrounding images, the method comprising: obtaining a plurality of environmental images captured by a plurality of vehicle-mounted cameras, and simultaneously receiving external images captured by external devices. Distinguishing the plurality of environmental images and the external images in to groups of image collections based on different view angles. After selecting a benchmark image of each group of image collections, a preset enhancement processing is utilized to enhance the benchmark image of each the group, and then all the enhanced benchmark images are stitched to generate an enhanced vehicle surrounding image.