Motion Gesture Recognition via Coordinate Transformation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motion sensing devices in portable electronic devices face challenges in accurately recognizing motion gestures due to the variability of sensor data from user to user, limited functionality, and the high cost and complexity of using sophisticated inertial sensors like gyroscopes and accelerometers.

Innovation Solution

The use of multiple rotational and linear motion sensors, transforming data from device coordinates to world coordinates, and employing feature detection to recognize gestures with reduced processing requirements, allowing for more flexible and robust gesture recognition across different operating modes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If low-cost inertial sensors are used, then device cost is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvedevice costVSAvoidsensor accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent transforms sensor data from device coordinates to world coordinates, changing the reference frame parameters to compensate for low-cost sensor limitations. This coordinate transformation allows the system to achieve better measurement precision by referencing motion against a stable external frame rather than the moving device itself

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary coordinate transformation layer between the low-cost sensors and the gesture recognition system. This intermediary processing layer compensates for sensor inaccuracies by translating raw sensor data into a more reliable reference frame, effectively bridging the gap between low-cost hardware and high-precision requirements

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If multiple motion sensors are used, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvemotion sensing accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines data from multiple motion sensors (accelerometers and gyroscopes) into a unified coordinate transformation process. By merging these sensor inputs and processing them together through a single transformation to world coordinates, the system achieves high measurement precision without proportionally increasing system complexity

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The world coordinate transformation system serves multiple functions simultaneously: it processes data from different sensor types, provides a common reference frame for gesture recognition, and enables various gesture types to be recognized using the same transformed data, reducing overall system complexity while maintaining high precision

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

3Measurement precision

If machine learning techniques are used for gesture recognition, then gesture recognition accuracy is improved, but processing resources increase

Engineering Contradiction:
Improvegesture recognition accuracyVSAvoidprocessing resources
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent performs coordinate transformation as a preliminary action before gesture recognition processing. By transforming sensor data to world coordinates in advance, the system creates pre-processed, more recognizable gesture patterns that reduce the computational burden on machine learning algorithms, thereby lowering processing resources while maintaining or improving recognition accuracy

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2350782B1Mobile devices with motion gesture recognition
Publication Date: 2019.04.10 INVENSENSE INC
  • EP2350782B1 patent drawingFigure 1
  • EP2350782B1 patent drawingFigure 2
  • EP2350782B1 patent drawingFigure 3A~4B

AI summary

Mobile devices using motion gesture recognition. In one aspect, processing motion to control a portable electronic device includes receiving, on the device, sensed motion data derived from motion sensors of the device and based on device movement in space. The motion sensors include at least three rotational motion sensors and at least three accelerometers. A particular operating mode is determined to be active while the movement of the device occurs, the mode being one of multiple different operating modes of the device. Motion gesture(s) are recognized from the motion data from a set of motion gestures available for recognition in the active operating mode. Each of the different operating modes, when active, has a different set of gestures available. State(s) of the device are changed based on the recognized gestures, including changing output of a display screen on the device.