Dual-Camera Marker Tracking for Low-Load Distal End Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for estimating the position of a movable unit's distal end require high computational load and continuous image capture by visual sensors, which is inefficient and resource-intensive.

Innovation Solution

The use of two visual sensors, a general-view camera and a hand-end camera, reading a projected marker to compute the position of the movable unit, reducing the computational load and enabling accurate grasping of objects without pre-existing shape data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a visual sensor constantly captures images and performs computational processing to estimate the position of the movable unit, then the position estimation accuracy is improved, but the processing load increases

Engineering Contradiction:
Improveposition estimation accuracyVSAvoidprocessing load
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

A marker is introduced as an intermediary object between the visual sensor and the movable unit. The marker serves as a reference that simplifies position estimation by providing known geometric features that are easier to process than directly analyzing the movable unit itself. This mediator reduces the computational complexity while maintaining measurement precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

Instead of directly processing complex images of the movable unit, the system uses a simplified representation through the marker. The marker acts as a copy or surrogate that contains the essential positional information in a more computationally tractable form, reducing the processing load while preserving the ability to accurately estimate position.

Inventive Principle:
Principle #26Copying

2Measurement precision

If the visual sensor continuously captures images of the movable unit, then the position estimation is improved, but the energy consumption increases

Engineering Contradiction:
Improveposition estimation accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The marker serves as an intermediary that enables position estimation with less frequent or less intensive imaging. By providing clear, predefined geometric features, the marker allows the system to achieve accurate position data without requiring continuous high-resolution image capture, thereby reducing energy consumption.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs position estimation based on partial information from the marker rather than requiring complete continuous imaging of the movable unit. This partial action approach - using only the marker features rather than full scene analysis - reduces the frequency and intensity of processing, lowering energy consumption while maintaining sufficient position accuracy.

Inventive Principle:
Principle #16Partial or excessive action

3Loss of information

If computational processing is performed on data from the first visual sensor, then the position information is obtained, but the processing time increases

Engineering Contradiction:
Improveposition informationVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The marker acts as an intermediary that provides position information in a format requiring minimal processing. The known geometry and features of the marker enable faster extraction of position data compared to analyzing arbitrary objects, thus reducing processing time while preventing loss of position information.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The marker is designed and positioned in advance with known geometric properties and features. This preliminary preparation of the reference object means that during operation, the system does not need to perform complex analysis - it only needs to match the observed marker features against the pre-known model, significantly reducing processing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3744484B1Information processing device, information processing method, and information processing system
Publication Date: 2023.07.05 SONY GROUP CORP
  • EP3744484B1 patent drawingFigure 1
  • EP3744484B1 patent drawingFigure 2
  • EP3744484B1 patent drawingFigure 3

AI summary

[Problem to be Solved] To estimate a position of a distal end of a movable unit with a reduced processing load. [Solution] Provided is an information processing apparatus including a position computer that computes, on the basis of first positional information obtained from reading of a projected marker by a first visual sensor and second positional information including positional information obtained from reading of the marker by a second visual sensor that moves relative to the first visual sensor, a position of a movable unit in which the second visual sensor is disposed. This makes it possible to estimate the position of the distal end of the movable unit with a reduced processing load.