Human activity recognition using inertial measurement units and smart shoes

2017 ◽  
Author(s):  
Prudhvi Tej Chinimilli ◽  
Sangram Redkar ◽  
Wenlong Zhang
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
Measurement Units

scholarly journals LARa: Creating a Dataset for Human Activity Recognition in Logistics Using Semantic Attributes

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4083
Author(s):  
Friedrich Niemann ◽  
Christopher Reining ◽  
Fernando Moya Rueda ◽  
Nilah Ravi Nair ◽  
Janine Anika Steffens ◽  
...  
Keyword(s):  
Motion Capture ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
The Past ◽  
Measurement Units ◽  
The Given ◽  
Semantic Attributes

Optimizations in logistics require recognition and analysis of human activities. The potential of sensor-based human activity recognition (HAR) in logistics is not yet well explored. Despite a significant increase in HAR datasets in the past twenty years, no available dataset depicts activities in logistics. This contribution presents the first freely accessible logistics-dataset. In the ’Innovationlab Hybrid Services in Logistics’ at TU Dortmund University, two picking and one packing scenarios were recreated. Fourteen subjects were recorded individually when performing warehousing activities using Optical marker-based Motion Capture (OMoCap), inertial measurement units (IMUs), and an RGB camera. A total of 758 min of recordings were labeled by 12 annotators in 474 person-h. All the given data have been labeled and categorized into 8 activity classes and 19 binary coarse-semantic descriptions, also called attributes. The dataset is deployed for solving HAR using deep networks.

scholarly journals Multimodal Database for Human Activity Recognition and Fall Detection

Proceedings ◽  
2018 ◽  
Vol 2 (19) ◽  
pp. 1237 ◽  
Author(s):  
Lourdes Martínez-Villaseñor ◽  
Hiram Ponce ◽  
Ricardo Abel Espinosa-Loera
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Wearable Sensors ◽  
Fall Detection ◽  
Human Activity Recognition ◽  
Data Sources ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
Detection Systems ◽  
Measurement Units

Fall detection can improve the security and safety of older people and alert when fall occurs. Fall detection systems are mainly based on wearable sensors, ambient sensors, and vision. Each method has commonly known advantages and limitations. Multimodal and data fusion approaches present a combination of data sources in order to better describe falls. Publicly available multimodal datasets are needed to allow comparison between systems, algorithms and modal combinations. To address this issue, we present a publicly available dataset for fall detection considering Inertial Measurement Units (IMUs), ambient infrared presence/absence sensors, and an electroencephalogram Helmet. It will allow human activity recognition researchers to do experiments considering different combination of sensors.

scholarly journals Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8337
Author(s):  
Hyeokhyen Kwon ◽  
Gregory D. Abowd ◽  
Thomas Plötz
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Large Scale ◽  
State Of The Art ◽  
Human Activity Recognition ◽  
The State ◽  
Model Parameters ◽  
Data Systems ◽  
Performance Improvements ◽  
Measurement Units

Supervised training of human activity recognition (HAR) systems based on body-worn inertial measurement units (IMUs) is often constrained by the typically rather small amounts of labeled sample data. Systems like IMUTube have been introduced that employ cross-modality transfer approaches to convert videos of activities of interest into virtual IMU data. We demonstrate for the first time how such large-scale virtual IMU datasets can be used to train HAR systems that are substantially more complex than the state-of-the-art. Complexity is thereby represented by the number of model parameters that can be trained robustly. Our models contain components that are dedicated to capture the essentials of IMU data as they are of relevance for activity recognition, which increased the number of trainable parameters by a factor of 1100 compared to state-of-the-art model architectures. We evaluate the new model architecture on the challenging task of analyzing free-weight gym exercises, specifically on classifying 13 dumbbell execises. We have collected around 41 h of virtual IMU data using IMUTube from exercise videos available from YouTube. The proposed model is trained with the large amount of virtual IMU data and calibrated with a mere 36 min of real IMU data. The trained model was evaluated on a real IMU dataset and we demonstrate the substantial performance improvements of 20% absolute F1 score compared to the state-of-the-art convolutional models in HAR.

scholarly journals Preferred Placement and Usability of a Smart Textile System vs. Inertial Measurement Units for Activity Monitoring

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2501 ◽  
Author(s):  
Mohammad Mokhlespour Esfahani ◽  
Maury Nussbaum
Keyword(s):  
Human Activity ◽  
Wearable Sensors ◽  
Activity Monitor ◽  
Activity Monitoring ◽  
Whole Body ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
Wearable Technologies ◽  
Smart Textile ◽  
Measurement Units

Wearable sensors and systems have become increasingly popular in recent years. Two prominent wearable technologies for human activity monitoring are smart textile systems (STSs) and inertial measurement units (IMUs). Despite ongoing advances in both, the usability aspects of these devices require further investigation, especially to facilitate future use. In this study, 18 participants evaluate the preferred placement and usability of two STSs, along with a comparison to a commercial IMU system. These evaluations are completed after participants engaged in a range of activities (e.g., sitting, standing, walking, and running), during which they wear two representatives of smart textile systems: (1) a custom smart undershirt (SUS) and commercial smart socks; and (2) a commercial whole-body IMU system. We first analyze responses regarding the usability of the STS, and subsequently compared these results to those for the IMU system. Participants identify a short-sleeved shirt as their preferred activity monitor. In additional, the SUS in combination with the smart socks is rated superior to the IMU system in several aspects of usability. As reported herein, STSs show promise for future applications in human activity monitoring in terms of usability.

scholarly journals Activity Recognition Using Multiple Inertial Measurement Units

IRBM ◽  
2016 ◽  
Vol 37 (3) ◽  
pp. 180-186 ◽  
Author(s):  
N. Jalloul ◽  
F. Porée ◽  
G. Viardot ◽  
P. L'Hostis ◽  
G. Carrault
Keyword(s):  
Activity Recognition ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
Measurement Units

scholarly journals Human Activity Recognition for Production and Logistics—A Systematic Literature Review

Information ◽  
2019 ◽  
Vol 10 (8) ◽  
pp. 245 ◽  
Author(s):  
Christopher Reining ◽  
Friedrich Niemann ◽  
Fernando Moya Rueda ◽  
Gernot A. Fink ◽  
Michael ten Hompel
Keyword(s):  
Literature Review ◽  
Activity Recognition ◽  
Human Activity ◽  
Systematic Literature Review ◽  
Human Activity Recognition ◽  
Sensor Technology ◽  
Road Map ◽  
Statistical Pattern ◽  
Measurement Units ◽  
Motion Capturing

This contribution provides a systematic literature review of Human Activity Recognition for Production and Logistics. An initial list of 1243 publications that complies with predefined Inclusion Criteria was surveyed by three reviewers. Fifty-two publications that comply with the Content Criteria were analysed regarding the observed activities, sensor attachment, utilised datasets, sensor technology and the applied methods of HAR. This review is focused on applications that use marker-based Motion Capturing or Inertial Measurement Units. The analysed methods can be deployed in industrial application of Production and Logistics or transferred from related domains into this field. The findings provide an overview of the specifications of state-of-the-art HAR approaches, statistical pattern recognition and deep architectures and they outline a future road map for further research from a practitioner’s perspective.

Sign in / Sign up

Export Citation Format

Share Document