scholarly journals Deep learning for vision‐based fall detection system: Enhanced optical dynamic flow

2020 ◽  
Author(s):  
Sagar Chhetri ◽  
Abeer Alsadoon ◽  
Thair Al‐Dala'in ◽  
P. W. C. Prasad ◽  
Tarik A. Rashid ◽  
...  
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Dynamic Flow

scholarly journals Robust Self-Adaptation Fall-Detection System Based on Camera Height

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3768 ◽  
Author(s):  
Kong ◽  
Chen ◽  
Wang ◽  
Chen ◽  
Meng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Daily Activities ◽  
Detection Methods ◽  
Depth Camera ◽  
Detection Accuracy ◽  
Data Set ◽  
Human Segmentation ◽  
Self Adaptation

Vision-based fall-detection methods have been previously studied but many have limitations in terms of practicality. Due to differences in rooms, users do not set the camera or sensors at the same height. However, few studies have taken this into consideration. Moreover, some fall-detection methods are lacking in terms of practicality because only standing, sitting and falling are taken into account. Hence, this study constructs a data set consisting of various daily activities and fall events and studies the effect of camera/sensor height on fall-detection accuracy. Each activity in the data set is carried out by eight participants in eight directions and taken with the depth camera at five different heights. Many related studies heavily depended on human segmentation by using Kinect SDK but this is not reliable enough. To address this issue, this study proposes Enhanced Tracking and Denoising Alex-Net (ETDA-Net) to improve tracking and denoising performance and classify fall and non-fall events. Experimental results indicate that fall-detection accuracy is affected by camera height, against which ETDA-Net is robust, outperforming traditional deep learning based fall-detection methods.

Fall Behavior Recognition Based on Deep Learning and Image Processing

2018 ◽  
Vol 9 (4) ◽  
pp. 1-15
Author(s):  
He Xu ◽  
Leixian Shen ◽  
Qingyun Zhang ◽  
Guoxu Cao
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
False Positive Rate ◽  
Fall Detection ◽  
The Elderly ◽  
Training Data ◽  
Local Network ◽  
Raspberry Pi ◽  
Behavior Recognition ◽  
Risk Of Death

Accidental fall detection for the elderly who live alone can minimize the risk of death and injuries. In this article, we present a new fall detection method based on "deep learning and image, where a human body recognition model-DeeperCut is used. First, a camera is used to get the detection source data, and then the video is split into images which can be input into DeeperCut model. The human key point data in the output map and the label of the pictures are used as training data to input into the fall detection neural network. The output model then judges the fall of the subsequent pictures. In addition, the fall detection system is designed and implemented with using Raspberry Pi hardware in a local network environment. The presented method obtains a 100% fall detection rate in the experimental environment. The false positive rate on the test set is around 1.95% which is very low and can be ignored because this will be checked by using SMS, WeChat and other SNS tools to confirm falls. Experimental results show that the proposed fall behavior recognition is effective and feasible to be deployed in home environment.

scholarly journals Highly-efficient fog-based deep learning AAL fall detection system

2020 ◽  
Vol 11 ◽  
pp. 100185 ◽  
Author(s):  
David Sarabia-Jácome ◽  
Regel Usach ◽  
Carlos E. Palau ◽  
Manuel Esteve
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Highly Efficient

scholarly journals NT-FDS—A Noise Tolerant Fall Detection System Using Deep Learning on Wearable Devices

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2006
Author(s):  
Marvi Waheed ◽  
Hammad Afzal ◽  
Khawir Mehmood
Keyword(s):  
Deep Learning ◽  
Missing Values ◽  
Short Term Memory ◽  
Detection System ◽  
Wearable Sensors ◽  
Fall Detection ◽  
The Elderly ◽  
Benchmark Datasets ◽  
Noise Tolerant ◽  
Local Interference

Given the high prevalence and detrimental effects of unintentional falls in the elderly, fall detection has become a pertinent public concern. A Fall Detection System (FDS) gathers information from sensors to distinguish falls from routine activities in order to provide immediate medical assistance. Hence, the integrity of collected data becomes imperative. Presence of missing values in data, caused by unreliable data delivery, lossy sensors, local interference and synchronization disturbances and so forth, greatly hamper the credibility and usefulness of data making it unfit for reliable fall detection. This paper presents a noise tolerant FDS performing in presence of missing values in data. The work focuses on Deep Learning (DL) particularly Recurrent Neural Networks (RNNs) with an underlying Bidirectional Long Short-Term Memory (BiLSTM) stack to implement FDS based on wearable sensors. The proposed technique is evaluated on two publicly available datasets—SisFall and UP-Fall Detection. Our system produces an accuracy of 97.21% and 97.41%, sensitivity of 96.97% and 99.77% and specificity of 93.18% and 91.45% on SisFall and UP-Fall Detection respectively, thus outperforming the existing state of the art on these benchmark datasets. The resultant outcomes suggest that the ability of BiLSTM to retain long term dependencies from past and future make it an appropriate model choice to handle missing values for wearable fall detection systems.

Sign in / Sign up

Export Citation Format

Share Document