A computer vision-approach for activity recognition and residential monitoring of elderly people
In this study, we explore a human activity recognition (HAR) system using computer vision for assisted living systems (ALS). Most existing HAR systems are implemented using wired or wireless sensor networks. These systems have limitations such as cost, power issues, weight, and the inability of the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Medicine in Novel Technology and Devices |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S259009352300067X |
| _version_ | 1797429661121118208 |
|---|---|
| author | Sudhir Gaikwad Shripad Bhatlawande Swati Shilaskar Anjali Solanke |
| author_facet | Sudhir Gaikwad Shripad Bhatlawande Swati Shilaskar Anjali Solanke |
| author_sort | Sudhir Gaikwad |
| collection | DOAJ |
| description | In this study, we explore a human activity recognition (HAR) system using computer vision for assisted living systems (ALS). Most existing HAR systems are implemented using wired or wireless sensor networks. These systems have limitations such as cost, power issues, weight, and the inability of the elderly to wear and carry them comfortably. These issues could be overcome by a computer vision based HAR system. But such systems require a highly memory-consuming image dataset. Training such a dataset takes a long time. The proposed computer-vision-based system overcomes the shortcomings of existing systems. The authors have used key-joint angles, distances between the key joints, and slopes between the key joints to create a numerical dataset instead of an image dataset. All these parameters in the dataset are recorded via real-time event simulation. The data set has 780,000 calculated feature values from 20,000 images. This dataset is used to train and detect five different human postures. These are sitting, standing, walking, lying, and falling. The implementation encompasses four distinct algorithms: the decision tree (DT), random forest (RF), support vector machine (SVM), and an ensemble approach. Remarkably, the ensemble technique exhibited exceptional performance metrics with 99 % accuracy, 98 % precision, 97 % recall, and an F1 score of 99 %. |
| first_indexed | 2024-03-09T09:16:22Z |
| format | Article |
| id | doaj.art-f3dcdb60c39847f188757a1ff584bc91 |
| institution | Directory Open Access Journal |
| issn | 2590-0935 |
| language | English |
| last_indexed | 2024-03-09T09:16:22Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Medicine in Novel Technology and Devices |
| spelling | doaj.art-f3dcdb60c39847f188757a1ff584bc912023-12-02T07:06:43ZengElsevierMedicine in Novel Technology and Devices2590-09352023-12-0120100272A computer vision-approach for activity recognition and residential monitoring of elderly peopleSudhir Gaikwad0Shripad Bhatlawande1Swati Shilaskar2Anjali Solanke3E&TC Department, Vishwakarma Institute of Technology, Pune, Maharashtra, India; Corresponding author.E&TC Department, Vishwakarma Institute of Technology, Pune, Maharashtra, IndiaE&TC Department, Vishwakarma Institute of Technology, Pune, Maharashtra, IndiaE&TC Department, Marathwada Mitramandal's College of Engineering, Pune, Maharashtra, IndiaIn this study, we explore a human activity recognition (HAR) system using computer vision for assisted living systems (ALS). Most existing HAR systems are implemented using wired or wireless sensor networks. These systems have limitations such as cost, power issues, weight, and the inability of the elderly to wear and carry them comfortably. These issues could be overcome by a computer vision based HAR system. But such systems require a highly memory-consuming image dataset. Training such a dataset takes a long time. The proposed computer-vision-based system overcomes the shortcomings of existing systems. The authors have used key-joint angles, distances between the key joints, and slopes between the key joints to create a numerical dataset instead of an image dataset. All these parameters in the dataset are recorded via real-time event simulation. The data set has 780,000 calculated feature values from 20,000 images. This dataset is used to train and detect five different human postures. These are sitting, standing, walking, lying, and falling. The implementation encompasses four distinct algorithms: the decision tree (DT), random forest (RF), support vector machine (SVM), and an ensemble approach. Remarkably, the ensemble technique exhibited exceptional performance metrics with 99 % accuracy, 98 % precision, 97 % recall, and an F1 score of 99 %.http://www.sciencedirect.com/science/article/pii/S259009352300067XAssisted living systemsHuman activity recognitionFall detectionKey joint angleLandmarks |
| spellingShingle | Sudhir Gaikwad Shripad Bhatlawande Swati Shilaskar Anjali Solanke A computer vision-approach for activity recognition and residential monitoring of elderly people Medicine in Novel Technology and Devices Assisted living systems Human activity recognition Fall detection Key joint angle Landmarks |
| title | A computer vision-approach for activity recognition and residential monitoring of elderly people |
| title_full | A computer vision-approach for activity recognition and residential monitoring of elderly people |
| title_fullStr | A computer vision-approach for activity recognition and residential monitoring of elderly people |
| title_full_unstemmed | A computer vision-approach for activity recognition and residential monitoring of elderly people |
| title_short | A computer vision-approach for activity recognition and residential monitoring of elderly people |
| title_sort | computer vision approach for activity recognition and residential monitoring of elderly people |
| topic | Assisted living systems Human activity recognition Fall detection Key joint angle Landmarks |
| url | http://www.sciencedirect.com/science/article/pii/S259009352300067X |
| work_keys_str_mv | AT sudhirgaikwad acomputervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT shripadbhatlawande acomputervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT swatishilaskar acomputervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT anjalisolanke acomputervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT sudhirgaikwad computervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT shripadbhatlawande computervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT swatishilaskar computervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople AT anjalisolanke computervisionapproachforactivityrecognitionandresidentialmonitoringofelderlypeople |