20230137198. APPROXIMATING MOTION CAPTURE OF PLURAL BODY PORTIONS USING A SINGLE IMU DEVICE simplified abstract (Celloscope Ltd.)
APPROXIMATING MOTION CAPTURE OF PLURAL BODY PORTIONS USING A SINGLE IMU DEVICE
Organization Name
Inventor(s)
Tamir Aloush of Kiryat Ono (IL)
APPROXIMATING MOTION CAPTURE OF PLURAL BODY PORTIONS USING A SINGLE IMU DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230137198 titled 'APPROXIMATING MOTION CAPTURE OF PLURAL BODY PORTIONS USING A SINGLE IMU DEVICE
Simplified Explanation
The patent application describes a system that captures the motion of a moving body using wearable sensors and processes the data to approximate the body's motion. The system utilizes generative adversarial networks to determine the physical feasibility and accuracy of candidate body motion trajectories.
- The system captures the motion of a moving body using wearable sensors called IMUs.
- IMU measurements are received by the system's interface.
- A processor analyzes the IMU measurements to approximate the body's motion during repetitive cycles.
- The processor derives a motion capture approximation output, including a trajectory set that describes the motion of different body portions.
- The trajectory set consists of multiple body portion trajectories.
- Generative adversarial networks are used to determine the physical feasibility and accuracy of candidate body motion trajectories.
- One network is trained to evaluate the physical feasibility of candidate trajectories for specific body portions.
- Another network is trained to assess how well candidate trajectories fit the IMU measurements.
Potential Applications
This technology has potential applications in various fields, including:
- Sports performance analysis: The system can be used to analyze the motion of athletes during training or competitions, providing valuable insights for improving performance and preventing injuries.
- Rehabilitation and physical therapy: By capturing and analyzing the motion of patients during rehabilitation exercises, the system can assist in designing personalized therapy programs and tracking progress.
- Virtual reality and gaming: The technology can enhance the realism and immersion of virtual reality experiences and gaming by accurately capturing and replicating body motion.
Problems Solved
The technology addresses several problems related to motion capture:
- Accuracy: By using IMUs and generative adversarial networks, the system improves the accuracy of motion capture approximations, providing more reliable data for analysis.
- Feasibility assessment: The system can determine the physical feasibility of candidate body motion trajectories, ensuring that the captured motion is realistic and physically possible.
- Efficiency: The use of generative adversarial networks allows for faster processing and analysis of motion data, reducing the time required for motion capture tasks.
Benefits
The technology offers several benefits:
- Improved motion capture: The system provides a more accurate approximation of body motion, allowing for better analysis and understanding of movement patterns.
- Real-time feedback: By processing IMU measurements in real-time, the system can provide immediate feedback on body motion, enabling athletes and patients to make adjustments and corrections during training or therapy sessions.
- Personalized analysis: The system can generate individualized motion capture approximations for different body portions, allowing for tailored analysis and feedback based on specific needs and goals.
Original Abstract Submitted
a system capturing motion of a moving body, including an imu interface to receive imu measurements from imu/s worn on the body; and a processor to derive, from the imu measurements, a motion capture approximation output including a trajectory, which describes a body portion’s motion during a cycle of repetitive motion, yielding a trajectory set including b body portion trajectories, wherein, to derive the trajectory set, the processor uses generative adversarial networks including one network trained to determine physical feasibility of candidate body portion trajectory/ies for body portion/s, from among multiple candidate body portion trajectories for the specific body portion; and another network trained to determine how well candidate body portion trajectory/ies fit/s the imu measurements.
