Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors
Human Activity Recognition (HAR) plays a vital role in applications such as healthcare, smart homes, and robotics, particularly in supporting the elderly. However, most existing HAR datasets focus on general human activities and are typically collected using RGB cameras in controlled environments wi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10945773/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849729636737482752 |
|---|---|
| author | Jongbum Park Kyoung Ok Yang Sunme Park Jun Won Choi |
| author_facet | Jongbum Park Kyoung Ok Yang Sunme Park Jun Won Choi |
| author_sort | Jongbum Park |
| collection | DOAJ |
| description | Human Activity Recognition (HAR) plays a vital role in applications such as healthcare, smart homes, and robotics, particularly in supporting the elderly. However, most existing HAR datasets focus on general human activities and are typically collected using RGB cameras in controlled environments with fixed angles—conditions that limit their real-world applicability. In this study, we introduce the Human Daily Indoor Actions (HDIA) dataset, specifically designed to capture natural indoor activities performed by elderly individuals. The dataset includes 48 daily actions, recorded using non-invasive infrared (IR) cameras and wearable armband sensors positioned at various angles to ensure diverse and realistic activity representation. The use of IR sensors enhances privacy, making the dataset ethically suitable for long-term monitoring. To demonstrate its utility, we implemented a fusion-based HAR model that integrates data from both IR and Inertial Measurement Unit (IMU) sensors. This model achieves strong activity recognition performance while minimizing the risk of identity exposure. By focusing on privacy-aware data collection and the daily routines of elderly individuals, the HDIA dataset offers a valuable resource for advancing real-world HAR research. |
| format | Article |
| id | doaj-art-fbf64f65a1d84f60b896cfe3c602210b |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-fbf64f65a1d84f60b896cfe3c602210b2025-08-20T03:09:09ZengIEEEIEEE Access2169-35362025-01-0113608226083210.1109/ACCESS.2025.355600110945773Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband SensorsJongbum Park0https://orcid.org/0009-0005-1161-6788Kyoung Ok Yang1https://orcid.org/0000-0002-8439-9834Sunme Park2https://orcid.org/0000-0002-1272-1900Jun Won Choi3https://orcid.org/0000-0002-3733-0148Department of Electrical Engineering, Hanyang University, Seoul, Seongdong-gu, South KoreaDepartment of Artificial Intelligence, Hanyang University, Seoul, Seongdong-gu, South KoreaIntelligent Robotics Research Center, Korea Electronics Technology Institute, Bundang-gu, Seongnam-si, Gyeonggi-do, South KoreaDepartment of Electrical and Computer Engineering, Seoul National University, Seoul, Gwanak-gu, South KoreaHuman Activity Recognition (HAR) plays a vital role in applications such as healthcare, smart homes, and robotics, particularly in supporting the elderly. However, most existing HAR datasets focus on general human activities and are typically collected using RGB cameras in controlled environments with fixed angles—conditions that limit their real-world applicability. In this study, we introduce the Human Daily Indoor Actions (HDIA) dataset, specifically designed to capture natural indoor activities performed by elderly individuals. The dataset includes 48 daily actions, recorded using non-invasive infrared (IR) cameras and wearable armband sensors positioned at various angles to ensure diverse and realistic activity representation. The use of IR sensors enhances privacy, making the dataset ethically suitable for long-term monitoring. To demonstrate its utility, we implemented a fusion-based HAR model that integrates data from both IR and Inertial Measurement Unit (IMU) sensors. This model achieves strong activity recognition performance while minimizing the risk of identity exposure. By focusing on privacy-aware data collection and the daily routines of elderly individuals, the HDIA dataset offers a valuable resource for advancing real-world HAR research.https://ieeexplore.ieee.org/document/10945773/Human action recognition (HAR)multimodal human action dataset (MHAD)IRinertial sensorselectromyography signalprivacy protection |
| spellingShingle | Jongbum Park Kyoung Ok Yang Sunme Park Jun Won Choi Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors IEEE Access Human action recognition (HAR) multimodal human action dataset (MHAD) IR inertial sensors electromyography signal privacy protection |
| title | Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors |
| title_full | Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors |
| title_fullStr | Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors |
| title_full_unstemmed | Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors |
| title_short | Human Daily Indoor Action (HDIA) Dataset: Privacy-Preserving Human Action Recognition Using Infrared Camera and Wearable Armband Sensors |
| title_sort | human daily indoor action hdia dataset privacy preserving human action recognition using infrared camera and wearable armband sensors |
| topic | Human action recognition (HAR) multimodal human action dataset (MHAD) IR inertial sensors electromyography signal privacy protection |
| url | https://ieeexplore.ieee.org/document/10945773/ |
| work_keys_str_mv | AT jongbumpark humandailyindooractionhdiadatasetprivacypreservinghumanactionrecognitionusinginfraredcameraandwearablearmbandsensors AT kyoungokyang humandailyindooractionhdiadatasetprivacypreservinghumanactionrecognitionusinginfraredcameraandwearablearmbandsensors AT sunmepark humandailyindooractionhdiadatasetprivacypreservinghumanactionrecognitionusinginfraredcameraandwearablearmbandsensors AT junwonchoi humandailyindooractionhdiadatasetprivacypreservinghumanactionrecognitionusinginfraredcameraandwearablearmbandsensors |