Driver Assistance System Virtual Camera Model for Blind Spot Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assistance systems for motor vehicles cannot reliably capture and display the environmental region, particularly failing to represent vehicles outside the camera's range or with fish-eye lenses, leading to non-intuitive and incorrect scene representations.

Innovation Solution

A method that identifies and replaces vehicles outside the camera's range with 3D models, allowing for customizable camera perspectives and maintaining accurate size ratios, using image data and object recognition algorithms to create a realistic three-dimensional representation of the environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If a third person perspective is created using only vehicle-side camera image data, then the driver can see the environmental region, but vehicles outside the camera's capturing range cannot be represented

Engineering Contradiction:
Improveinformation about vehicles outside camera rangeVSAvoidcamera system configuration
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the motor vehicle and its surrounding environmental region in a three-dimensional computer-generated model. This virtual representation allows the system to display vehicles and objects that are outside the physical camera's capturing range by rendering them based on the virtual camera's perspective, thereby preventing information loss without adding physical cameras.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transitions from two-dimensional camera images to a three-dimensional virtual environment. By creating a 3D model of the motor vehicle and its surroundings, the system can represent objects from any angle and position, including those outside the original camera's field of view, thus recovering information that would otherwise be lost.

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

2Area of stationary object

If cameras with fish-eye lenses are used to increase capturing range, then more of the environmental region is visible, but size perception of objects becomes distorted

Engineering Contradiction:
Improvecapturing range of cameraVSAvoidsize perception of objects
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent creates a virtual copy of the motor vehicle and its surrounding environmental region in a three-dimensional computer-generated model. This virtual representation allows the system to display vehicles and objects that are outside the physical camera's capturing range by rendering them based on the virtual camera's perspective, thereby preventing information loss without adding physical cameras.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transforms the distorted image data from fish-eye lenses into a virtual three-dimensional environment where objects are represented with accurate size ratios. By rendering the virtual model from the perspective of a virtual camera positioned on the motor vehicle, the system corrects the size distortion inherent in fish-eye lens images while maintaining the wide capturing range.

Inventive Principle:
Principle #35Parameter changes

3Area of stationary object

If multiple cameras are combined or stitched to expand coverage, then more environmental region is captured, but information is lost when objects change between capturing ranges

Engineering Contradiction:
Improvecapturing rangeVSAvoidinformation about objects in blind spots
Core Design Contradiction:
Area of stationary objectVSLoss of information

Solution Approach 1:

The patent creates a virtual copy of the motor vehicle and its surrounding environmental region in a three-dimensional computer-generated model. This virtual representation allows the system to display vehicles and objects that are outside the physical camera's capturing range by rendering them based on the virtual camera's perspective, thereby preventing information loss without adding physical cameras.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent merges the image data from multiple physical cameras into a unified virtual three-dimensional model of the environmental region. By stitching the images and creating a coherent virtual environment, the system eliminates blind spots and ensures continuous representation of objects as they move between camera fields of view, preventing information loss at the boundaries.

Inventive Principle:
Principle #5Merging (Combining)

4Adaptability or versatility

If the virtual camera position is moved to show different perspectives, then the driver can see different areas, but vehicles outside the new capturing range are lost

Engineering Contradiction:
Improvecamera perspectiveVSAvoidinformation about vehicles outside virtual camera range
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent creates a virtual copy of the motor vehicle and its surrounding environmental region in a three-dimensional computer-generated model. This virtual representation allows the system to display vehicles and objects that are outside the physical camera's capturing range by rendering them based on the virtual camera's perspective, thereby preventing information loss without adding physical cameras.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3497616B1Method for assisting a driver of a motor vehicle in driving the motor vehicle, driver assistance system as well as motor vehicle
Publication Date: 2020.06.03 CONNAUGHT ELECTRONICS
  • EP3497616B1 patent drawingFigure 1~2
  • EP3497616B1 patent drawingFigure 3a~3b
  • EP3497616B1 patent drawingFigure 3c~3d

AI summary

The invention relates to a method for assisting a driver of a motor vehicle (1) in driving the motor vehicle (1), wherein based on image data (17) captured from an environmental region (5) of the motor vehicle (1) by at least one vehicle-side camera (3), at least one image (B1, B2, B3, B4, B5, B6) of the environmental region (5) is created for displaying on a vehicle-side display device (10), wherein another vehicle (16) in the environmental region (5) is identified based on the image data (17) and the other vehicle (16) is replaced with a model (M) of a vehicle in the at least one image (B1, B2, B3, B4, B5, B6) of the environmental region (5). In addition, the invention relates to a driver assistance system (2) as well as to a motor vehicle (1).