Skeleton Detection System for Multi-Operator Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing skeleton detection systems face challenges in accurately identifying a specific operator among multiple operators in image data, leading to potential misidentification and increased processing load, especially when operators' behaviors change.

Innovation Solution

A skeleton detection system that includes a first storage unit for reference operation information, a skeleton information detection unit to identify skeleton data from working videos, and a target identification unit to pinpoint operators whose actions align within a preset allowable operation range, reducing the system's processing load by leveraging the regularity and periodicity of repetitive operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If image data capturing multiple operators is analyzed by the computer, then the inspection system can monitor multiple operators simultaneously, but the operator identification accuracy decreases and the processing load increases

Engineering Contradiction:

Improvenumber of operators inspected simultaneouslyVSAvoidoperator identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the complex task of identifying and inspecting multiple operators by first detecting skeleton information for each operator separately, then selecting candidate operators based on skeleton characteristics, and finally identifying target operators through comparison with reference operation information. This segmentation reduces confusion between multiple operators and lowers processing load.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by first detecting skeleton information for all operators in the image data before proceeding to identification and inspection. The skeleton information detection serves as a preliminary filtering step that reduces the number of operators requiring detailed analysis, thereby improving both accuracy and efficiency.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If image data with higher capacity is used for inspection, then the inspection accuracy improves, but the processing load on the system increases

Engineering Contradiction:

Improveinspection accuracyVSAvoidprocessing load

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the necessary skeleton information from the full image data, focusing on key body parts and their movements. This extraction process eliminates unnecessary image processing while retaining the essential information needed for accurate inspection, thereby reducing processing load without sacrificing inspection accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the parameter representation from full image data to skeleton information, which is a more compact and computationally efficient format. By transforming the data representation, the system achieves accurate inspection with reduced processing requirements.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If the system processes all detected skeleton information for identification, then the target identification accuracy improves, but the processing time increases

Engineering Contradiction:

Improvetarget identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary selection of candidate operators based on skeleton information characteristics before conducting the detailed target identification process. This preliminary action filters out non-target operators, reducing the number of comparisons needed while maintaining identification accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies partial action by comparing reference operation information only with candidate operators identified through skeleton analysis, rather than comparing with all detected operators. This selective comparison reduces processing time while maintaining sufficient accuracy for identifying target operators.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20230109640A1Skeleton detection system and work management device

Publication Date: 2023.04.06 DAICEL CORP

AI summary

A skeleton detection system includes, a first storage unit configured to store reference operation information related to at least one cycle of a reference operation being a repetitive operation performed by an operator, a skeleton information detection unit configured to detect skeleton information about the operator from a working video obtained by capturing the operator during work, and a target identification unit configured to identify, as a target, among pieces of skeleton information about a plurality of operators during work, detected by the skeleton information detection unit, skeleton information about an operator indicating an operation satisfying a target requirement that a difference between the reference operation information and inspection target information being operation information during work falls within a preset allowable operation range.