Dimensional measuring device, dimensional measuring system, and dimensional measuring method

The dimension measuring device uses a pre-trained segmentation base model combined with additional layers to efficiently measure object dimensions, addressing the inefficiencies of existing systems by minimizing preparation time and ensuring accurate measurements.

JP2026084268APending Publication Date: 2026-05-21FUJI ELECTRIC CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
FUJI ELECTRIC CO LTD
Filing Date
2024-11-11
Publication Date
2026-05-21

AI Technical Summary

Technical Problem

Existing dimension measuring devices require extensive preparation time due to the need to create and update multiple models for each object to be measured, especially when the object changes, leading to inefficiencies in measurement processes.

Method used

A dimension measuring device that utilizes a segmentation base model pre-trained with vast learning data, combined with additional layers learned on specific objects, allowing for rapid adaptation and accurate dimension measurement without recreating the entire model for each object.

Benefits of technology

Enables dimension measurement of various objects with minimal preparation time by leveraging pre-trained base models and additional layers, reducing the need for extensive learning and manual input, while ensuring accurate segmentation and dimension calculation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026084268000001_ABST
    Figure 2026084268000001_ABST
Patent Text Reader

Abstract

This invention provides a dimensional measuring device, a dimensional measuring system, and a dimensional measuring method that enable the measurement of the dimensions of various objects visible in a target image with minimal preparation time. [Solution] This dimensional measuring device 100 includes a learning unit 11 that generates an additional layer that learns the object to be measured 4a using an additional learning dataset L that includes a learning data image 1 showing the object to be learned 1a, a model selection unit 13 that selects a combined model M by combining the additional layer R1 with the segmentation base model B, a boundary line identification unit 14 that identifies the contour of the object to be measured 4a that has undergone segmentation processing as boundary line positions, and a dimension calculation unit 15 that calculates the distance between the boundary line positions of the object to be measured 4a as dimensions. The learning unit 11 is configured to learn the parameters of the additional layers R1 to R3 while fixing the parameters of the segmentation base model B during learning.
Need to check novelty before this filing date? Find Prior Art