Detection of sitting posture using hierarchical image composition and deep learning

Kulikajevas, Audrius; Maskeliūnas, Rytis; Damaševičius, Robertas

doi:10.7717/peerj-cs.442

Cited by 69 publications

(33 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in the work presented in [41] the authors implemented a computer vision system with a Deep Learning Convolutional Neural Network classifier, specifically a model based on Mobilenet v2. The study was conducted with 11 participants and the model achieved 68.3% accuracy classifying six sitting postures.…”

Section: Related Workmentioning

confidence: 99%

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

Nowadays, the percentage of time that the population spends sitting has increased substantially due to the use of computers as the main tool for work or leisure and the increase in jobs with a high office workload. As a consequence, it is common to suffer musculoskeletal pain, mainly in the back, which can lead to both temporary and chronic damage. This pain is related to holding a posture during a prolonged period of sitting, usually in front of a computer. This work presents a IoT posture monitoring system while sitting. The system consists of a device equipped with Force Sensitive Resistors (FSR) that, placed on a chair seat, detects the points where the user exerts pressure when sitting. The system is complemented with a Machine Learning model based on Artificial Neural Networks, which was trained to recognize the neutral correct posture as well as the six most frequent postures that involve risk of damage to the locomotor system. In this study, data was collected from 12 participants for each of the seven positions considered, using the developed sensing device. Several neural network models were trained and evaluated in order to improve the classification effectiveness. Hold-Out technique was used to guide the training and evaluation process. The results achieved a mean accuracy of 81% by means of a model consisting of two hidden layers of 128 neurons each. These results demonstrate that is feasible to distinguish different sitting postures using few sensors allocated in the surface of a seat, which implies lower costs and less complexity of the system.

show abstract

Section: Related Workmentioning

confidence: 99%

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Therefore, the proposed approach for long term detection of human posture consist of multi-sensors and LoRa [60]. Finally, Kulikajevas [61] proposed a novel deep learning model based on the MobileNetV2 for remove the current problem of posture detection related to visibility of human such as occlusion. The approach received accuracy of 91.47%.…”

Section: Related Workmentioning

confidence: 99%

Novel Ensemble Algorithm for Multiple Activity Recognition in Elderly People Exploiting Ubiquitous Sensing Devices

et al. 2021

View full text Add to dashboard Cite

Ambient assisted living is good way to look after ageing population that enables us to detect human's activities of daily living (ADLs) and postures, as number of older adults are increasing at rapid pace. Posture detection is used to provide the assessment for monitoring the activity of elderly people. Most of the existing approaches exploit dedicated sensing devices as as cameras, thermal sensors, accelerometer, gyroscope, magnetometer and so on. Traditional methods such as recording data using these sensors, training and testing machine learning classifiers to identify various human postures. This paper exploits data recorded using ubiquitous devices such as smart phones we use on daily basis and classify different human activities such as standing, sitting, laying, walking, walking downstairs and walking upstairs. Moreover, we have used machine learning and deep learning classifiers including random forest, KNN, logistic regression, multilayer perceptron, decision tree, QDA and SVM, convolutional neural network and long short-term memory as ground truth and proposed a novel ensemble classification algorithm to classify each human activity. The proposed algorithm demonstrate classification accuracy of 98% that outperforms other algorithms.

show abstract

“…However, all prior approaches all revolve around reconstructing quite static objects and not dynamically morphing meshes such as human body. Some approaches dealing with human body prediction using depth information exist [40][41][42][43] however their body predictions do not deal with full body reconstruction and only pose estimation.…”

Section: Related Workmentioning

confidence: 99%

HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction

Kulikajevas

Maskeliūnas

Damaševičius

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Majority of current research focuses on a single static object reconstruction from a given pointcloud. However, the existing approaches are not applicable to real world applications such as dynamic and morphing scene reconstruction. To solve this, we propose a novel two-tiered deep neural network architecture, which is capable of reconstructing self-obstructed human-like morphing shapes from a depth frame in conjunction with cameras intrinsic parameters. The tests were performed using on custom dataset generated using a combination of AMASS and MoVi datasets. The proposed network achieved Jaccards’ Index of 0.7907 for the first tier, which is used to extract region of interest from the point cloud. The second tier of the network has achieved Earth Mover’s distance of 0.0256 and Chamfer distance of 0.276, indicating good experimental results. Further, subjective reconstruction results inspection shows strong predictive capabilities of the network, with the solution being able to reconstruct limb positions from very few object details.

show abstract

Detection of sitting posture using hierarchical image composition and deep learning

Cited by 69 publications

References 66 publications

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

Novel Ensemble Algorithm for Multiple Activity Recognition in Elderly People Exploiting Ubiquitous Sensing Devices

HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction

Contact Info

Product

Resources

About