180 likes | 309 Views
This project, supervised by Dr. Manolya Kavakli and conducted by student Alexey Novoselov, explores the development of a Sensor Jacket for gesture recognition in virtual reality environments. Despite its potential, existing Motion Capture technologies lack convenient software for analysis. This study aims to collect and analyze output data, develop a mathematical model, and create an algorithm to process signals. The focus includes addressing the challenges posed by noise and signal non-linearity while leveraging contemporary piezo-electric technologies for enhanced sensor functionality.
E N D
Wearable Sensor Analysis for Gesture Recognition Supervisor: Dr. Manolya Kavakli Student: Alexey Novoselov St. ID: 41650883
Agenda 1: Background; 2: Goals; 3: Intended Outcomes; 4: Significance; 5: Approach; 6: Contemporary Technologies; 7: Piezo-Electric Technology; 8: Problems; 9: Experiments; 10: Output Data; 11: Initial Analysis; 12: Mathematical Approach; 13: Algorithmic Approach; 14: Conclusion 15: Future Work
1: Background • Virtual Reality is very promising scientific area; • Needs tools for interaction; • A lot of various technologies and devices; • Sensor Jacket is one of them; • No appropriate software for output analysis;
2: Goals • Investigate contemporary Motion Capture technologies and techniques; • Collect Sensor Jacket’s output data; • Analyze it; • Develop a mathematical model or an algorithm for Sensor Jacket;
3: Intended Outcomes • The list of justified experiments; • Data, collected during the set of experiments; • General characteristics of signals; • Application of mathematical approach; • Application of algorithmic approach; • Mathematical model or algorithm for signal processing;
4: Significance • Other Motion Capture systems not very convenient in use; • Sensor Jacket is wearable; • Sensor Jacket is simple; • But is has no software for output analysis;
5: Approach • Develop and perform experiments; • Collect data; • Filter data; • Analyze data; • Develop a tool;
6: Contemporary Technologies • Optical; • Inertial; • Mechanical;
7: Piezo-Electric Technology • Piezo-effect; • Piezo-electric sensor; • Made of graphite and silicone rubber;
8: Problems • Only static characteristic provided; • Electric noise in the output channels; • Strongly non-linear output signal; • Speed dependent;
11: Initial Analysis • Minimal (Starting) value; • Maximal (Peak) value; • Steady Value; • The overshoot; • Difference between initial and final values;
12: Mathematical Approach • Basic characteristics; • Speed of the signal change; • Angle of slope of the signal; • Area of the signal;
13: Algorithmic Approach • Determine the active sensors; • Calculate the area of their signals; • Calculate the speed of sensors’ signals change; • Using the graphs (Figures 18-20), calculate the real speed of movement; • Using the tables of active sensors, determine to which types of movement (AoF, AoS, or AStF) this motion belongs; • Determine the approximate direction of movement; • Calculate the average time between the start and the peak of transient process for each group of sensors, forming the movement type; • Using the information from steps 4, 5, and 6, calculate the approximate distance that operator’s hand has passed during the motion in each direction; • Calculate the final coordinates of operator’s palm using formulas;
14: Conclusion • Technologies review; • Designed and performed experiments; • Collected, filtered, and analysed data; • Mathematical approach did not succeed; • Algorithm created;
15: Future Work • More experiments; • More sensitive data filtration; • Use advanced mathematical techniques; • Create more accurate and precise tool.