Camera System Reference Point Determination for Distance and Speed

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the distance and relative speed of a target object relative to a motor vehicle from camera images are computationally expensive and complex, making them inefficient for real-time applications in motor vehicles.

Innovation Solution

A method that defines a baseline in the transition area between the target object and the ground surface, using characteristic features like Harris points and optical flow vectors, to determine a reference point for calculating distance and speed, reducing computational effort and enabling precise and fast determination without relying on illuminant invariance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If characteristic features are extracted from images and a reference point is determined using existing methods (e.g., illuminant invariance), then distance and speed determination is achieved, but computational effort and complexity increase significantly

Engineering Contradiction:
Improvedistance and speed determination accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential information needed for distance and speed determination by defining a baseline in the transition area between target object and ground surface. Instead of processing all characteristic features or relying on complex illuminant invariance calculations, the method extracts specifically the baseline position and reference point, significantly reducing computational complexity while maintaining measurement precision.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The image processing is segmented into distinct steps: first identifying the transition area between target object and ground, then defining a baseline within this transition area, and finally determining the reference point on the baseline. This segmentation allows each step to be computationally efficient while collectively achieving accurate distance and speed measurements.

Inventive Principle:
Principle #1Segmentation

2Productivity

If complex methods based on illuminant invariance are used to determine the reference point, then distance and speed can be calculated, but the computational power requirements increase making real-time implementation difficult

Engineering Contradiction:
Improvereal-time processing capabilityVSAvoidcomputational power consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by determining only the necessary reference point information rather than performing complete illuminant invariance calculations across the entire image. By focusing computational resources on identifying the baseline in the transition area and extracting the reference point, the method achieves real-time processing capability with reduced computational power consumption.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If a reference point is determined for each target object using traditional methods, then distance and relative speed can be determined, but the computational effort increases with the number of target objects

Engineering Contradiction:
Improvedistance and speed measurement accuracyVSAvoidprocessing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts only the critical baseline information from the transition area between target object and ground surface, rather than performing comprehensive feature extraction and analysis for each target object. This extraction approach maintains measurement accuracy for distance and speed while significantly improving processing efficiency, especially when multiple target objects are present.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11236991B2Method for determining a current distance and/or a current speed of a target object based on a reference point in a camera image, camera system and motor vehicle
Publication Date: 2022.02.01 CONNAUGHT ELECTRONICS
  • US11236991B2 patent drawing
  • US11236991B2 patent drawing
  • US11236991B2 patent drawing

AI summary

A method for determining a current distance and/or a current speed of a target object relative to a motor vehicle based on an image of the target object, in which the image is provided by a camera of the motor vehicle, where characteristic features of the target object are extracted from the image and a reference point associated with the target object is determined based on the characteristic features for determining the distance and/or the speed, wherein the distance and/or the speed are determined based on the reference point, and a baseline is determined in the image based on the characteristic features, which is in a transition area from the depicted target object to a ground surface depicted in the image, and a point located on the baseline is determined as the reference point.