Optical Object Identification Using Image Superposition and Feature Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for identifying usage objects are inaccurate and costly due to reliance on optical and data-related details, leading to errors in comparison with database entries.

Innovation Solution

A method involving a processing unit that captures and classifies usage objects by obtaining characteristic values, comparing them with database entries, and superimposing camera images with database objects to achieve precise identification, using a weighting formula for partial characteristic values and allowing for optical or data-technical comparisons.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If optical comparison methods are used to identify usage objects, then the process is inexpensive, but the accuracy is low due to dependence on small optical details

Engineering Contradiction:
Improveidentification accuracyVSAvoidoptical detail sensitivity
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent segments the identification process into multiple independent characteristic value extractions (color, shape, texture, size) rather than relying on a single optical comparison. Each characteristic is extracted and evaluated separately, then combined to form a comprehensive identification result, reducing sensitivity to small variations in any single optical detail

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms the identification approach from direct optical image comparison to comparison of extracted characteristic parameters (color values, shape metrics, texture features). This parameter transformation makes the identification process more robust to optical variations while maintaining accuracy

Inventive Principle:
Principle #35Parameter changes

2Reliability

If detailed optical comparison is performed to improve identification accuracy, then reliability increases, but time consumption and cost increase

Engineering Contradiction:
Improveidentification accuracyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary extraction of characteristic values (color, shape, texture, size) from the usage object before the actual identification comparison. These pre-extracted features are stored and can be quickly compared against database entries, avoiding the need for repeated complex optical analysis during the identification process itself

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent extracts essential characteristic values (color, shape, texture, size) from the complete optical image, separating the critical identification features from unnecessary visual information. This extraction process creates a simplified representation that can be compared efficiently while maintaining identification accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3726425B1Method for physical, in particular optical, detection of at least one application object
Publication Date: 2023.10.11 GARCIA MARKUS
  • EP3726425B1 patent drawingFigure 1~2A
  • EP3726425B1 patent drawingFigure 2B~2C
  • EP3726425B1 patent drawingFigure 3A~3B

AI summary

The invention relates to a method for the physical, in particular optical, detection of at least one object of use, comprising the step of carrying out at least one physical detection process, for example by a user and/or a device for carrying out the detection, in particular at least one photograph, of the object of use, such that the object of use is detected in such a way that an image of the object of use captured by the detection process is displayed simultaneously, identically or scaled identically to the database object displayed on a screen, wherein by the detection process the object of use is assigned by the processing unit and/or the CPU and/or the user to at least one class of object of use, for example a vehicle type.