Marker-Based Operation Region Calculation for Input Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems face challenges in accurately recognizing user input operations from hand movements captured in images, often leading to incorrect or missed input recognition.

Innovation Solution

An information processing system that includes a marker attached to the user, a sensor mounted on the user, and an information processing apparatus with an operation region calculation unit and a recognition unit. The system calculates an operation region based on the marker's position and detects the position or motion of an operation body within this region using sensor data to accurately recognize input operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If hand motion analysis is performed on the entire captured image, then the system can detect all hand movements, but it cannot differentiate between input operations and other hand movements, leading to recognition errors

Engineering Contradiction:
Improveinput operation recognition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The captured image is divided into multiple regions of interest based on marker positions. Instead of analyzing the entire image, the system focuses only on specific regions where input operations are likely to occur, thereby improving recognition accuracy while reducing computational complexity

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different regions of the image are assigned different analysis priorities based on their relevance to input operations. Regions containing markers or expected operation areas receive enhanced analysis, while other areas are processed with lower priority or skipped entirely

Inventive Principle:
Principle #3Local quality

2Measurement precision

If the operation region is calculated based on marker position, then the recognition accuracy is improved, but the device complexity increases due to additional sensors and processing

Engineering Contradiction:
Improveoperation detection accuracyVSAvoidsystem configuration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Markers are introduced as intermediary elements that facilitate the calculation of operation regions. These markers serve as reference points that enable the system to define regions of interest without requiring complex sensor arrays, thus improving accuracy while managing system complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The markers and sensors are designed to serve multiple functions: they not only define operation regions but also provide reference frames for motion analysis, enable tracking of operation bodies, and assist in distinguishing input operations from other movements

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10296101B2Information processing system, information processing apparatus, control method, and program
Publication Date: 2019.05.21 NEC CORP
  • US10296101B2 patent drawing
  • US10296101B2 patent drawing
  • US10296101B2 patent drawing

AI summary

A marker (3020) is any part of a user's body or is any mark attached to the user. A sensor (3040) is attached to the user. An operation region calculation unit (2020) calculates an operation region included in a captured image on the basis of a position of the marker (3020) included in the captured image generated by a camera. A recognition unit (2040) calculates a position or motion of an operation body captured in the operation region, and recognizes an input operation on the basis of the calculated position or motion of the operation body. Note that the recognition unit (2040) calculates a position of the operation body captured in the operation region at a timing based on a result of detection by the sensor (3040). The recognition unit (2040) calculates motion of the operation body captured in the operation region in a period including a timing based on a result of detection by the sensor (3040).