Fusing Object Information and Inertial Data for Activity Recognition
In the field of pervasive computing, wearable devices have been widely used for recognizing human activities. One important area in this research is the recognition of activities of daily living where especially inertial sensors and interaction sensors (like RFID tags with scanners) are popular choi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/19/4119 |
| _version_ | 1798042361896370176 |
|---|---|
| author | Alexander Diete Heiner Stuckenschmidt |
| author_facet | Alexander Diete Heiner Stuckenschmidt |
| author_sort | Alexander Diete |
| collection | DOAJ |
| description | In the field of pervasive computing, wearable devices have been widely used for recognizing human activities. One important area in this research is the recognition of activities of daily living where especially inertial sensors and interaction sensors (like RFID tags with scanners) are popular choices as data sources. Using interaction sensors, however, has one drawback: they may not differentiate between proper interaction and simple touching of an object. A positive signal from an interaction sensor is not necessarily caused by a performed activity e.g., when an object is only touched but no interaction occurred afterwards. There are, however, many scenarios like medicine intake that rely heavily on correctly recognized activities. In our work, we aim to address this limitation and present a multimodal egocentric-based activity recognition approach. Our solution relies on object detection that recognizes activity-critical objects in a frame. As it is infeasible to always expect a high quality camera view, we enrich the vision features with inertial sensor data that monitors the users’ arm movement. This way we try to overcome the drawbacks of each respective sensor. We present our results of combining inertial and video features to recognize human activities on different types of scenarios where we achieve an F 1 -measure of up to 79.6%. |
| first_indexed | 2024-04-11T22:34:28Z |
| format | Article |
| id | doaj.art-02d1729eb3934fcb8fa1d444df169377 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:34:28Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-02d1729eb3934fcb8fa1d444df1693772022-12-22T03:59:15ZengMDPI AGSensors1424-82202019-09-011919411910.3390/s19194119s19194119Fusing Object Information and Inertial Data for Activity RecognitionAlexander Diete0Heiner Stuckenschmidt1Data and Web Science Group, University of Mannheim, 68159 Mannheim, GermanyData and Web Science Group, University of Mannheim, 68159 Mannheim, GermanyIn the field of pervasive computing, wearable devices have been widely used for recognizing human activities. One important area in this research is the recognition of activities of daily living where especially inertial sensors and interaction sensors (like RFID tags with scanners) are popular choices as data sources. Using interaction sensors, however, has one drawback: they may not differentiate between proper interaction and simple touching of an object. A positive signal from an interaction sensor is not necessarily caused by a performed activity e.g., when an object is only touched but no interaction occurred afterwards. There are, however, many scenarios like medicine intake that rely heavily on correctly recognized activities. In our work, we aim to address this limitation and present a multimodal egocentric-based activity recognition approach. Our solution relies on object detection that recognizes activity-critical objects in a frame. As it is infeasible to always expect a high quality camera view, we enrich the vision features with inertial sensor data that monitors the users’ arm movement. This way we try to overcome the drawbacks of each respective sensor. We present our results of combining inertial and video features to recognize human activities on different types of scenarios where we achieve an F 1 -measure of up to 79.6%.https://www.mdpi.com/1424-8220/19/19/4119activity recognitionmachine learningmulti-modality |
| spellingShingle | Alexander Diete Heiner Stuckenschmidt Fusing Object Information and Inertial Data for Activity Recognition Sensors activity recognition machine learning multi-modality |
| title | Fusing Object Information and Inertial Data for Activity Recognition |
| title_full | Fusing Object Information and Inertial Data for Activity Recognition |
| title_fullStr | Fusing Object Information and Inertial Data for Activity Recognition |
| title_full_unstemmed | Fusing Object Information and Inertial Data for Activity Recognition |
| title_short | Fusing Object Information and Inertial Data for Activity Recognition |
| title_sort | fusing object information and inertial data for activity recognition |
| topic | activity recognition machine learning multi-modality |
| url | https://www.mdpi.com/1424-8220/19/19/4119 |
| work_keys_str_mv | AT alexanderdiete fusingobjectinformationandinertialdataforactivityrecognition AT heinerstuckenschmidt fusingobjectinformationandinertialdataforactivityrecognition |