Yarn Spindle Trolley Detection Using Masked Image Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The manual sampling detection method for yarn spindles during storage has a high missed detection rate and is inefficient.

Innovation Solution

A detection method utilizing image acquisition and analysis to compare entering and leaving images of a trolley, employing mask plates to identify differences in spindle count, and using a target detection model to automate the detection process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual sampling detection is used on trolleys leaving the designated area, then the detection process can be performed with simple equipment and operations, but the detection efficiency is low and the missed detection rate is high

Engineering Contradiction:
Improvedetection efficiencyVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces the manual mechanical detection system with an automated image-based detection system. Image acquisition devices capture images of yarn spindles on trolleys, and image processing algorithms automatically analyze these images to detect spindle presence and quantity, eliminating the need for manual sampling and significantly improving both efficiency and accuracy

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates visual copies (images) of the yarn spindles using image acquisition devices. These images serve as digital representations that can be analyzed without physically handling or moving the spindles, enabling non-contact detection that preserves the original objects while providing accurate detection data

Inventive Principle:
Principle #26Copying

2Loss of time

If manual sampling detection is performed on trolleys, then the detection method is simple to implement, but it requires significant manpower and time consumption

Engineering Contradiction:
Improvedetection timeVSAvoiddetection system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent implements continuous detection by capturing images of trolleys as they leave the designated area. The image acquisition and processing system operates continuously without interruption, analyzing each trolley in real-time as it passes through the detection zone, thereby eliminating the time loss associated with intermittent manual sampling

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The detection system performs self-service by automatically acquiring images, processing them through algorithms, and generating detection results without requiring human operators. The system autonomously completes the entire detection workflow, from image capture to analysis, significantly reducing manpower requirements

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4672168A1Detection method and apparatus, and storage medium
Publication Date: 2025.12.31 ZHEJIANG HENGYI PETROCHEMICAL CO LTD
  • EP4672168A1 patent drawingFigure 1~2
  • EP4672168A1 patent drawingFigure 3~4
  • EP4672168A1 patent drawingFigure 5~6

AI summary

A detection method and apparatus, and a storage medium are provided, relating to a field of data processing technology. The method includes: obtaining (S101) a first entering image and a first leaving image when detecting that a target trolley leaves a target area; obtaining (S102) a target entering mask image of the first entering image and a target leaving mask image of the first leaving image, wherein the target entering mask image is obtained by using a mask plate to mask an area where each yarn spindle is located in the first entering image, and the target leaving mask image is obtained by using a mask plate to mask an area where each yarn spindle is located in the first leaving image; and obtaining (S103) detection information of the target trolley based on difference information between the target entering mask image and the target leaving mask image.