Action Recognition Using Distance Measuring Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for recognizing user actions, particularly those using inertial sensors, face challenges such as drift and offset issues, which degrade the accuracy of action recognition.
Innovation Solution
The use of distance measuring sensors, either alone or in combination with inertial and proximity sensors, to acquire and analyze data for improved action recognition, including the attachment of multiple sensors to users and objects to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If inertial sensors are used for action recognition, then the system can detect user motion, but the accuracy deteriorates due to drift and offset issues
Solution Approach 1:
The patent combines multiple sensor types (distance measuring sensors, inertial sensors, and proximity sensors) into an integrated sensing system. This fusion allows the system to cross-validate measurements and compensate for the drift and offset issues inherent in inertial sensors alone, thereby maintaining reliable and accurate action recognition over extended periods.
Solution Approach 2:
The patent introduces distance measuring sensors as intermediary devices that provide absolute position references. These sensors act as mediators between the user's physical actions and the recognition system, offering stable measurement benchmarks that correct the cumulative errors of inertial sensors and improve overall measurement precision.
2Measurement precision
If multiple sensors are used to improve action recognition accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent designs a multi-functional sensor system where each sensor type serves multiple purposes. For example, distance measuring sensors not only provide position data but also help calibrate and correct inertial sensor drift. This multi-functionality allows the system to achieve high measurement precision without proportionally increasing complexity, as the same sensors perform multiple roles in the action recognition process.
Data Source
AI summary
Provided is an information processing device including a sensor control unit that acquires distance measuring sensor data detected by a plurality of distance measuring sensors and a data processing unit that obtains action recognition results of one or a plurality of users by analyzing the distance measuring sensor data. The information processing device further includes an output control unit that controls output based on the action recognition result.