Model Pattern Evaluation for Accurate Symmetrical Object Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object detection technologies struggle to accurately determine the position and posture of symmetrical objects in images due to subjective user judgment in setting the regions that characterize these features, leading to potential errors in detection.

Innovation Solution

An object detection device that utilizes a model pattern evaluation system to calculate the geometric distribution of features, setting features of interest based on evaluation values to enhance position and angle detection accuracy by comparing the model pattern with extracted image features, and adjusting the relative position, orientation, and scale for precise matching.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a second region characterizing position and posture is set by console operation based on user judgment, then the detection process can be implemented, but the detection accuracy deteriorates due to potential user error in selecting unsuitable regions

Engineering Contradiction:

Improveease of setting detection regionVSAvoidposition and posture detection accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs self-service by automatically selecting the second region through computational analysis of feature distribution and detection ability evaluation, eliminating the need for manual user selection and thereby avoiding user error while maintaining ease of implementation

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-evaluating multiple candidate regions using feature distribution analysis and detection ability calculations before actual detection, selecting the optimal region in advance to ensure both accuracy and ease of operation

Inventive Principle:

Principle #10Preliminary action

2Loss of time

If features are selected based on subjective user judgment, then the detection system can be configured quickly, but the reliability of detection deteriorates due to potential selection of inappropriate features

Engineering Contradiction:

Improvetime for configuring detection systemVSAvoiddetection reliability

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system replaces the mechanical process of manual feature selection with an automated computational system that evaluates feature distribution and detection ability objectively, maintaining quick configuration while significantly improving detection reliability through algorithmic optimization

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes parameters by using objective computational metrics (feature distribution statistics, detection ability scores) instead of subjective user judgment, enabling rapid automated configuration that ensures reliable feature selection through mathematical optimization

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If all features are treated equally in degree of coincidence calculation, then the calculation process is simple, but the detection accuracy deteriorates for symmetrical objects where certain features are more informative

Engineering Contradiction:

Improvecalculation process complexityVSAvoidposition and angle detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system applies local quality by assigning different weights to different features based on their individual detection ability and information content, allowing the calculation process to focus more on informative features while maintaining overall simplicity and improving accuracy for symmetrical objects

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12361582B2Object detection device and model pattern evaluation device

Publication Date: 2025.07.15 FANUC LTD

AI summary

A model pattern evaluation device for a robotic system comprises a processor. The processor is configured to: receive an image in which a target object is represented captured by a camera attached to a movable robotic component of the robotic system; calculate, for detecting the target object from the image, an evaluation value representing a geometric distribution of a plurality of features in a model pattern, the model pattern corresponding to the target object; set, among the plurality of features, a first feature for detecting a position in a specific direction of the target object in the image or a second feature for detecting an angle in a rotational direction centered about a predetermined point of the target object in the image as a feature of interest based on the evaluation value; and generate a detection result based on the first or second features to control the movable robotic component.