Fingertip Pointing Angle Detection via 3D Viewpoint Transformation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems for detecting hand movements to control operations, such as in vehicles, often require users to change their posture or lack intuitive operation due to inaccuracies in calculating hand movements without considering the sensor's orientation and positional relationship with the user.

Innovation Solution

An information processing apparatus that calculates three-dimensional coordinates of a user's fingertip and transforms them into a different viewpoint to determine the angle of pointing, using a camera to improve accuracy and user operability by considering the sensor's orientation and positional relationship.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If three-dimensional coordinates are calculated from camera images without viewpoint transformation, then calculation process is simple, but measurement precision deteriorates due to sensor orientation and positional relationship inaccuracies

Engineering Contradiction:
Improvefingertip pointing angle accuracyVSAvoidcoordinate transformation process
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms three-dimensional fingertip coordinates from the camera's viewpoint into a different reference viewpoint coordinate system. This dimensional transformation accounts for the camera's orientation and positional relationship with the user, thereby improving the accuracy of fingertip pointing angle measurements while managing the complexity through systematic coordinate transformation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If hand movement detection is implemented without considering sensor orientation, then ease of operation improves, but measurement precision deteriorates due to inaccurate hand movement detection

Engineering Contradiction:
Improvehand movement detection accuracyVSAvoidoperation intuitiveness
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent introduces a coordinate transformation process as an intermediary between the camera's raw coordinate data and the final hand movement interpretation. This intermediary step adjusts for the camera's orientation and position, providing accurate hand movement detection that maintains operational intuitiveness by presenting corrected, user-relevant coordinate information.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If fingertip angle calculation is performed without viewpoint transformation, then processing time is reduced, but measurement precision deteriorates due to sensor positional variations

Engineering Contradiction:
Improvepointing angle calculation accuracyVSAvoidcoordinate transformation processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary coordinate transformation of the three-dimensional fingertip coordinates from the camera viewpoint to a different reference viewpoint before calculating the pointing angle. This preliminary action pre-adjusts the coordinates to account for camera orientation and position, ensuring accurate angle calculation while minimizing repeated transformation needs during subsequent processing.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260057543A1Information processing apparatus, information processing method, and computer-readable medium
Publication Date: 2026.02.26 PANASONIC AUTOMOTIVE SYST CO LTD
  • US20260057543A1 patent drawing
  • US20260057543A1 patent drawing
  • US20260057543A1 patent drawing

AI summary

An information processing apparatus according to an aspect of the present disclosure includes a memory in which a program is stored, and a processor coupled to the memory and configured to perform processing by executing the program. The processing including: acquiring an image captured by a camera and including a fingertip with which a user points to a target; calculating three-dimensional coordinates of the fingertip at a camera viewpoint from the image; transforming the three-dimensional coordinates of the fingertip at the camera viewpoint into three-dimensional coordinates of the fingertip at a viewpoint different from the camera viewpoint; and calculating an angle at which the fingertip points to the target, based on two-dimensional coordinates of the fingertip excluding a depth direction identified from the three-dimensional coordinates of the fingertip at the different viewpoint.