Scout Imaging Range Specification with Adaptive Feature-Point Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing imaging systems face challenges in accurately detecting feature points on subjects during scout imaging due to subject movement and partial coverage, which can lead to inaccuracies in specifying the imaging range for three-dimensional image acquisition.

Innovation Solution

An information processing apparatus that selects between a first detection model prioritizing frame rate and a second model prioritizing accuracy based on the imaging part and movement of the subject to detect feature points and specify the imaging range, with the first model having a higher processing speed and the second model providing higher accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a single detection model is used for feature point detection, then the system is simple to operate, but the detection accuracy decreases when the subject moves or is partially covered

Engineering Contradiction:
Improveease of operationVSAvoiddetection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system dynamically switches between different detection models based on real-time conditions such as subject movement and coverage status. The controller selects the first detection model when the subject is stationary and fully visible, and switches to the second detection model when movement or partial coverage is detected, optimizing detection accuracy for varying operational conditions.

Inventive Principle:
Principle #15Dynamics

2Productivity

If the first detection model prioritizing frame rate is used, then the processing speed is high, but the detection accuracy is lower

Engineering Contradiction:
Improveprocessing speedVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system dynamically adjusts the detection model selection based on subject stability. When the subject is stationary and fully visible, the first detection model with higher frame rate is used for efficient processing. When movement or partial coverage is detected, the system switches to the second detection model that prioritizes accuracy, thus optimizing the trade-off between processing speed and detection accuracy according to real-time conditions.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If the second detection model prioritizing accuracy is used, then the detection accuracy is high, but the processing speed is lower

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system employs conditional switching between detection models. The second detection model with higher accuracy is selectively activated only when the controller detects subject movement or partial coverage, rather than running continuously. This dynamic approach ensures high detection accuracy is achieved when needed, while maintaining higher processing speeds during normal stable conditions.

Inventive Principle:
Principle #15Dynamics

4Measurement precision

If manual setting of imaging range is performed, then the imaging range can be precisely adjusted, but the operation time increases

Engineering Contradiction:
Improveimaging range precisionVSAvoidoperation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic imaging range specification by detecting feature points and calculating the imaging range based on the detected positions. This self-service approach eliminates the need for manual operator intervention in setting the imaging range, thereby reducing operation time while maintaining precision through accurate feature point detection using the selected detection models.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4578398A1Information processing apparatus, information processing method, and information processing program
Publication Date: 2025.07.02 FUJIFILM CORP
  • EP4578398A1 patent drawingFigure 1
  • EP4578398A1 patent drawingFigure 2~3
  • EP4578398A1 patent drawingFigure 4

AI summary

A processor (11) acquires a camera image generated by capturing a moving image of a subject on an examination table via a camera (7), selects one detection model from among a plurality of detection models including a first detection model that places importance on a frame rate in a case of detecting the feature points and a second detection model that places importance on accuracy in a case of detecting the feature points, which are constructed so as to detect a plurality of feature points on the subject included in the camera image, detects the plurality of feature points on the subject included in the camera image by using the selected detection model, and specifies an imaging range of the subject based on the plurality of feature points.