Fall Detection and Motion Analysis Using Visual Approaches
Falls are considered one of the most ubiquitous problems leading to morbidity and disability in the elderly. This paper presents a vision-based approach toward the care and rehabilitation of the elderly by examining the important body symmetry features in falls and activities of daily living (AD...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Indonesia
2022-11-01
|
| Series: | International Journal of Technology |
| Subjects: | |
| Online Access: | https://ijtech.eng.ui.ac.id/article/view/5840 |
| _version_ | 1797965815853613056 |
|---|---|
| author | Xin Lin Lau Tee Connie Michael Kah Ong Goh Siong Hoe Lau |
| author_facet | Xin Lin Lau Tee Connie Michael Kah Ong Goh Siong Hoe Lau |
| author_sort | Xin Lin Lau |
| collection | DOAJ |
| description | Falls are considered
one of the most ubiquitous problems leading to morbidity and disability in the
elderly. This paper presents a vision-based approach toward the care and
rehabilitation of the elderly by examining the important body symmetry features
in falls and activities of daily living (ADL). The proposed method carries out
human skeleton estimation and detection on image datasets for feature extraction
to predict falls and to analyze gait motion. The extracted skeletal information
is further evaluated and analyzed for the fall risk factors in order to predict
a fall event. Four critical risk factors are found to be highly correlated to
falls, including 2D motion (gait speed), gait pose, 3D trunk angle or body
orientation, and body shape (width-to-height ratio). Different variants of deep
architectures, including 1D Convolutional Neural Network (CNN), Long Short-Term
Memory (LSTM) Network, Gated Recurrent Units (GRU) model, and attention-based
mechanism, are investigated with several fusion techniques to predict the fall
based on human body balance study. A given test gait sequence will be
classified into one of the three phases: non-fall, pre-impact fall, and fall.
With the attention-based GRU architecture, an accuracy of 96.2% can be achieved
for predicting a falling event. |
| first_indexed | 2024-04-11T02:06:02Z |
| format | Article |
| id | doaj.art-2a91054a61e14399a50e2f921a79bbf1 |
| institution | Directory Open Access Journal |
| issn | 2086-9614 2087-2100 |
| language | English |
| last_indexed | 2024-04-11T02:06:02Z |
| publishDate | 2022-11-01 |
| publisher | Universitas Indonesia |
| record_format | Article |
| series | International Journal of Technology |
| spelling | doaj.art-2a91054a61e14399a50e2f921a79bbf12023-01-03T03:03:13ZengUniversitas IndonesiaInternational Journal of Technology2086-96142087-21002022-11-011361173118210.14716/ijtech.v13i6.58405840Fall Detection and Motion Analysis Using Visual ApproachesXin Lin Lau0Tee Connie1Michael Kah Ong Goh2Siong Hoe Lau3Faculty of Information Science & Technology, Multimedia University, 75450, Melaka, MalaysiaFaculty of Information Science & Technology, Multimedia University, 75450, Melaka, MalaysiaFaculty of Information Science & Technology, Multimedia University, 75450, Melaka, MalaysiaFaculty of Information Science & Technology, Multimedia University, 75450, Melaka, MalaysiaFalls are considered one of the most ubiquitous problems leading to morbidity and disability in the elderly. This paper presents a vision-based approach toward the care and rehabilitation of the elderly by examining the important body symmetry features in falls and activities of daily living (ADL). The proposed method carries out human skeleton estimation and detection on image datasets for feature extraction to predict falls and to analyze gait motion. The extracted skeletal information is further evaluated and analyzed for the fall risk factors in order to predict a fall event. Four critical risk factors are found to be highly correlated to falls, including 2D motion (gait speed), gait pose, 3D trunk angle or body orientation, and body shape (width-to-height ratio). Different variants of deep architectures, including 1D Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) Network, Gated Recurrent Units (GRU) model, and attention-based mechanism, are investigated with several fusion techniques to predict the fall based on human body balance study. A given test gait sequence will be classified into one of the three phases: non-fall, pre-impact fall, and fall. With the attention-based GRU architecture, an accuracy of 96.2% can be achieved for predicting a falling event.https://ijtech.eng.ui.ac.id/article/view/5840attention mechanismdeep learningfall detectiongated recurrent unit (gru)vision approach |
| spellingShingle | Xin Lin Lau Tee Connie Michael Kah Ong Goh Siong Hoe Lau Fall Detection and Motion Analysis Using Visual Approaches International Journal of Technology attention mechanism deep learning fall detection gated recurrent unit (gru) vision approach |
| title | Fall Detection and Motion Analysis Using Visual Approaches |
| title_full | Fall Detection and Motion Analysis Using Visual Approaches |
| title_fullStr | Fall Detection and Motion Analysis Using Visual Approaches |
| title_full_unstemmed | Fall Detection and Motion Analysis Using Visual Approaches |
| title_short | Fall Detection and Motion Analysis Using Visual Approaches |
| title_sort | fall detection and motion analysis using visual approaches |
| topic | attention mechanism deep learning fall detection gated recurrent unit (gru) vision approach |
| url | https://ijtech.eng.ui.ac.id/article/view/5840 |
| work_keys_str_mv | AT xinlinlau falldetectionandmotionanalysisusingvisualapproaches AT teeconnie falldetectionandmotionanalysisusingvisualapproaches AT michaelkahonggoh falldetectionandmotionanalysisusingvisualapproaches AT sionghoelau falldetectionandmotionanalysisusingvisualapproaches |