Vehicle Surround View Display Using Historical Images for Artifact Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods fail to effectively reduce image artifacts caused by dynamic objects in vehicle surroundings, particularly those in close proximity, leading to distorted and unrecognizable views.

Innovation Solution

Capture current camera images, detect dynamic objects using distance sensors and machine learning, store historical image data, and adapt the position of historical image data based on vehicle movement to replace artifact areas in the captured images, projecting them onto a virtual projection surface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If coordinate transformation and projection onto a projection surface is applied to display camera images, then the surrounding environment can be visualized on a display device, but nearby objects become stretched and unrecognizable due to the Manhattan effect

Engineering Contradiction:
Improverecognizability of nearby objectsVSAvoiddistortion of nearby objects
Core Design Contradiction:
Loss of informationVSShape

Solution Approach 1:

The patent applies preliminary action by shifting the vertical part of the projection surface towards the vehicle before projecting the camera image. This pre-adjustment of the projection surface position compensates for the upcoming distortion, enabling nearby objects to be displayed at their correct positions and scales before the coordinate transformation occurs, thus preventing the Manhattan effect

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies local quality by differentiating the treatment of different regions in the projection surface. Specifically, the vertical part of the projection surface corresponding to nearby objects is shifted towards the vehicle, while other regions remain unchanged. This localized adjustment ensures that only the affected areas are corrected, maintaining overall image accuracy while fixing the distortion of nearby objects

Inventive Principle:
Principle #3Local quality

2Reliability

If conventional artifact reduction methods are applied to static objects, then display accuracy is improved, but artifacts caused by dynamic objects in proper motion remain unaddressed

Engineering Contradiction:
Improveaccuracy of artifact reductionVSAvoidapplicability to dynamic objects
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by making the projection surface adaptable and changeable based on object characteristics. Instead of a fixed projection surface, the system dynamically adjusts the position of the vertical part of the projection surface towards the vehicle when dynamic objects are detected. This dynamic adaptation allows the same system to effectively handle both static and dynamic objects, improving versatility while maintaining reliability

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS12373927B2Method for reducing image artifacts in a display of the surrounding environment of a vehicle, computer program, computing device, and vehicle
Publication Date: 2025.07.29 ROBERT BOSCH GMBH
  • US12373927B2 patent drawing
  • US12373927B2 patent drawing
  • US12373927B2 patent drawing

AI summary

A method for reducing image artifacts in a display of the environment of a vehicle. The method includes: capturing at least one current camera image of the environment of the vehicle; detecting an object in the environment of the vehicle; ascertaining the position and/or movement of the object relative to the vehicle; ascertaining a movement of the vehicle; storing at least a partial area of the captured camera image as historical image data which depicts a predetermined area of the environment of the vehicle, wherein the current position relative to the vehicle is assigned to the historical image data, wherein an object area of the currently captured camera image which corresponds to the ascertained position and/or movement of the detected object is not stored as historical image data; adapting the position relative to the vehicle assigned to the stored image data depending on the ascertained movement of the vehicle.