Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data
Accurate human activity recognition is a challenging topic of research in many areas. A common approach to activity recognition is to use accelerometers and/or gyroscopes to detect trunk or leg movement. This paper present a novel approach to detect human activities based on thigh angle computed usi...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
N/A
2014
|
| Subjects: | |
| Online Access: | http://www.ipin2014.org/wp/pdf/2A-2.pdf http://hdl.handle.net/20.500.11937/34678 |
| _version_ | 1848754288517447680 |
|---|---|
| author | Abhayasinghe, Kahala Murray, Iain |
| author2 | N/A |
| author_facet | N/A Abhayasinghe, Kahala Murray, Iain |
| author_sort | Abhayasinghe, Kahala |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Accurate human activity recognition is a challenging topic of research in many areas. A common approach to activity recognition is to use accelerometers and/or gyroscopes to detect trunk or leg movement. This paper present a novel approach to detect human activities based on thigh angle computed using data from a single thigh mounted Inertial Measurement Unit (IMU). As this work forms a component of a system underdevelopment to assist the vision impaired in indoor navigation, activities common in indoor pedestrian tracking such as sitting, standing and walking were considered in the development of the algorithm. This algorithm uses simple signal processing techniques including peak detection, zero crossing detection and timers to identify the activity based on the thigh angle computed by fusing accelerometer and gyroscope. This allows implantation of the algorithm in a general purpose low end microcontroller. To reduce the number of input parameters to the algorithm, it was assumed that accelerometer y–axis is aligned with the thigh such that gyroscopic x–data represents angular velocity of the forward and backward movement of the thigh. The algorithm has shown above 78% accuracy in detecting standing, above 92%accuracy for walking and no measured errors for sitting, in a test conducted with a limited number of samples with ideal testing conditions. These results indicate that this less computationally intense algorithm gives promising results in activity detection in indoor pedestrian navigation applications. |
| first_indexed | 2025-11-14T08:38:02Z |
| format | Conference Paper |
| id | curtin-20.500.11937-34678 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:38:02Z |
| publishDate | 2014 |
| publisher | N/A |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-346782017-01-30T13:45:00Z Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data Abhayasinghe, Kahala Murray, Iain N/A indoor navigation inertial sensors activity recognition Human gait analysis Accurate human activity recognition is a challenging topic of research in many areas. A common approach to activity recognition is to use accelerometers and/or gyroscopes to detect trunk or leg movement. This paper present a novel approach to detect human activities based on thigh angle computed using data from a single thigh mounted Inertial Measurement Unit (IMU). As this work forms a component of a system underdevelopment to assist the vision impaired in indoor navigation, activities common in indoor pedestrian tracking such as sitting, standing and walking were considered in the development of the algorithm. This algorithm uses simple signal processing techniques including peak detection, zero crossing detection and timers to identify the activity based on the thigh angle computed by fusing accelerometer and gyroscope. This allows implantation of the algorithm in a general purpose low end microcontroller. To reduce the number of input parameters to the algorithm, it was assumed that accelerometer y–axis is aligned with the thigh such that gyroscopic x–data represents angular velocity of the forward and backward movement of the thigh. The algorithm has shown above 78% accuracy in detecting standing, above 92%accuracy for walking and no measured errors for sitting, in a test conducted with a limited number of samples with ideal testing conditions. These results indicate that this less computationally intense algorithm gives promising results in activity detection in indoor pedestrian navigation applications. 2014 Conference Paper http://hdl.handle.net/20.500.11937/34678 http://www.ipin2014.org/wp/pdf/2A-2.pdf N/A restricted |
| spellingShingle | indoor navigation inertial sensors activity recognition Human gait analysis Abhayasinghe, Kahala Murray, Iain Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title | Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title_full | Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title_fullStr | Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title_full_unstemmed | Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title_short | Human Activity Recognition Using Thigh Angle Derived from Single Thigh Mounted IMU Data |
| title_sort | human activity recognition using thigh angle derived from single thigh mounted imu data |
| topic | indoor navigation inertial sensors activity recognition Human gait analysis |
| url | http://www.ipin2014.org/wp/pdf/2A-2.pdf http://hdl.handle.net/20.500.11937/34678 |