Object Presence Detection Using Representative Point Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing object detection systems face challenges in maintaining measurement accuracy while reducing processing time due to excessive thinning of image signals, which degrades positional relationship measurement between moving bodies and obstacles.

Innovation Solution

An object detection device comprising an output unit, detection units, first and second data generation units, and an information processing unit, where the device generates and processes data to extract only necessary information for object presence, reducing data quantity and improving processing speed without compromising accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If image signals are thinned out by dividing the image into regions and limiting feature points per region, then processing time is reduced, but measurement accuracy of positional relationship is degraded

Engineering Contradiction:
Improveprocessing timeVSAvoidmeasurement accuracy of positional relationship
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The patent extracts only the necessary feature points (those contributing to object contour definition) from the thinned image signals, rather than uniformly limiting all feature points. This selective extraction maintains measurement accuracy for critical positional relationships while reducing overall data volume for processing.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different processing strategies to different regions based on their importance. Regions containing object contours or critical feature points are preserved with higher fidelity, while less important regions undergo more aggressive thinning. This local differentiation maintains accuracy where needed while reducing processing time elsewhere.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If all image signals are processed to maintain measurement accuracy, then measurement accuracy is maintained, but processing time increases

Engineering Contradiction:
Improvemeasurement accuracy of positional relationshipVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts and processes only the essential feature points that contribute to positional relationship measurement, rather than processing all image signals. This extraction approach maintains the necessary measurement accuracy while significantly reducing the total processing load and time required.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial processing to the image signals - processing all signals initially to ensure no critical information is lost, then selectively thinning out redundant signals. This partial action approach ensures measurement accuracy is maintained while avoiding the excessive processing time that would result from processing all signals in full detail.

Inventive Principle:
Principle #16Partial or excessive 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

The solution enables faster information processing while maintaining measurement accuracy, allowing for high-speed detection of object presence and shape without using complex calculations.

Implementation Method 1

a plurality of detection units detect a second signal that occurs due to the first signal being reflected by the object

Methodology Applied
Scientific EffectReflection: Reflection

Data Source

PatentEP3432259B1Object detection device, object detection method, and program
Publication Date: 2023.11.08 OMRON CORP
  • EP3432259B1 patent drawingFigure 1
  • EP3432259B1 patent drawingFigure 2
  • EP3432259B1 patent drawingFigure 3

AI summary

The purpose of the present invention is to improve the speed of processing related to the presence of objects, while maintaining measurement accuracy of object detection, in an object detection device. This object detection device 100 is provided with: an output unit 141; a plurality of detection units 143-1, 143-2, ..., 143-n; a first data generation unit 152; a second data generation unit 153; and an information processing unit 154. The output unit 141 outputs measurement light Lm. The plurality of detection units detect reflected light Lr. The first data generation unit 152 generates first data D1. The second data generation unit generates second data D2 by extracting, from the first data D1, a plurality of pieces of second position information, which are pieces of first position information that correspond to representative points expressing the presence ranges of objects O. The information processing unit 154 uses the second data D2 to execute information processing related to the presence of the objects O.