Motor Vehicle Vision System Window Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motor vehicle vision systems face challenges in balancing detection efficiency with limited processing and memory resources, requiring a cost-effective solution.

Innovation Solution

The vision system cuts out a window from the entire image area within the image sensor, reducing data transfer, processing, and storage by transmitting only the cut-out window for further processing, with adjustable window parameters based on the relative orientation of the imaging device, particularly beneficial in stereo vision systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If the entire image area is transmitted to electronic processing means, then complete image information is available for processing, but data transfer volume, processing load, and memory consumption increase significantly

Engineering Contradiction:
Improveimage information completenessVSAvoiddata volume
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent extracts only the relevant portion of the image (the window containing the detected object or region of interest) from the complete image area captured by the imaging device. This extraction is performed at the image sensor level, where a window function selectively transmits only the necessary image data to the electronic processing means, thereby reducing data volume while preserving essential information for vision tasks.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different quality levels to different regions of the image. The region of interest (within the window) is processed with high detail and resolution, while the rest of the image area is either discarded or processed with lower detail. This local quality approach ensures that computational resources are concentrated on the most important parts of the scene, optimizing the balance between information completeness and processing efficiency.

Inventive Principle:
Principle #3Local quality

2Device complexity

If window parameters are fixed for all imaging devices, then system complexity is reduced, but processing efficiency decreases due to misalignment in stereo vision systems

Engineering Contradiction:
Improveparameter setting complexityVSAvoidimage processing efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent implements dynamic window parameters that adapt to the specific characteristics of each imaging device and its orientation. Rather than using fixed parameters for all devices, the system adjusts window position, size, and shape based on individual device calibration data, relative orientations, and field-of-view characteristics. This dynamic adaptation optimizes processing efficiency for stereo vision systems while managing complexity through automated parameter determination.

Inventive Principle:
Principle #15Dynamics

3Quantity of substance

If the window is cut out in image processing procedures behind the image sensor, then data reduction is achieved, but additional processing steps and memory buffer requirements increase

Engineering Contradiction:
Improvedata volumeVSAvoidprocessing procedure complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent performs the windowing operation preliminarily, at the earliest possible stage in the imaging pipeline - directly at the image sensor output before data is transmitted to external processing units. This preliminary action reduces the total data volume that needs to be transferred and processed downstream, eliminating the need for additional memory buffering and reducing processing complexity in subsequent stages.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach reduces latency and memory consumption during image alignment and matching, enabling faster and more efficient processing with reduced data handling, thus providing a reliable and cost-efficient vision system.

Implementation Method 1

image sensor means the electronic device where the detected radiation is converted into an electric signal

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Data Source

PatentEP2254091B1Vision system and method for a motor vehicle
Publication Date: 2020.03.25 VEONEER SWEDEN AB
  • EP2254091B1 patent drawingFigure 1
  • EP2254091B1 patent drawingFigure 2

AI summary

A vision system (10) for a motor vehicle comprises at least one imaging device (12) adapted to detect images from a region surrounding the motor vehicle, and an electronic processing means (14) for processing image data provided by the imaging device (12), wherein the imaging device (12) comprises an image sensor (21). The vision system (10) is adapted to input window parameters to the image sensor (21) for cutting out and outputting a window image part (32) of the complete image area (30) of said image sensor (21).