Motion Determination Apparatus Using Segmented Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current motion determination systems are inefficient in monitoring and determining user motions in predetermined procedures, particularly in self-fueling stations and coin-parking facilities, as they lack the capability to quickly and accurately assess the correctness of user actions.

Innovation Solution

A motion determination apparatus and method that specifies a person's position and characteristic motions using image data, analyzing these motions against pre-defined patterns to determine if they are performed in the correct order, incorporating a position specifying means, motion specifying means, and determination means to ensure accurate and efficient assessment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If image data is analyzed to determine user motions in self-fueling stations, then motion monitoring capability is improved, but determination speed and efficiency deteriorate

Engineering Contradiction:
Improvemotion monitoring capabilityVSAvoiddetermination speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the image data analysis process into distinct stages: first specifying the person's position in the image, then identifying characteristic motions based on that position, and finally determining the sequence of motions. This segmentation allows each stage to be processed independently and efficiently, improving overall determination speed while maintaining monitoring capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs preliminary action by pre-defining characteristic motion patterns associated with specific positions in the image. Instead of analyzing all possible motions from scratch, the system prepares motion patterns in advance for different positions (e.g., fueling position, payment position), enabling faster real-time determination by simply matching observed motions against these pre-prepared patterns.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If comprehensive image data analysis is performed to ensure accurate motion determination, then determination accuracy is improved, but processing time increases

Engineering Contradiction:
Improvedetermination accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies local quality by focusing analysis on specific regions and characteristics relevant to each position. Instead of analyzing the entire image comprehensively, the system identifies the person's position first, then analyzes only the characteristic motions relevant to that specific position. This localized approach maintains high determination accuracy while significantly reducing processing time by avoiding unnecessary analysis of irrelevant image areas.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent extracts only the essential characteristic motions needed for determination at each position, rather than processing all image data. By identifying and extracting specific motion patterns (e.g., nozzle handling, cap removal) associated with each position, the system achieves accurate determination while minimizing processing time through selective analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS20240420506A1Motion determination apparatus, motion determination method, and non-transitory computer readable medium
Publication Date: 2024.12.19 NEC CORP
  • US20240420506A1 patent drawing
  • US20240420506A1 patent drawing
  • US20240420506A1 patent drawing

AI summary

Provided is a motion determination apparatus and the like that can determine a motion of a person faster and more efficiently. A motion determination apparatus includes a position specifying means for specifying a position of a person from acquired image data, a motion specifying means for specifying a first characteristic motion by analyzing a motion of the person in the image data in accordance with a first characteristic motion pattern associated with a first position of the specified person, and specifying a second characteristic motion by analyzing a motion of the person in the image data in accordance with a second characteristic motion pattern associated with a second position of the specified person, and a determination means for determining whether the specified characteristic motion is in a predetermined order.