Abstract
Human fall detection plays a vital part in the design of sensor based alarming system, aid physical therapists not only to lessen after fall effect and also to save human life. Accurate and timely identification can offer quick medical services to the injured people and prevent from serious consequences. Several vision-based approaches have been developed by the placement of cameras in diverse everyday environments. At present times, deep learning (DL) models particularly convolutional neural networks (CNNs) have gained much importance in the fall detection tasks. With this motivation, this paper presents a new vision based elderly fall event detection using deep learning (VEFED-DL) model. The proposed VEFED-DL model involves different stages of operations namely preprocessing, feature extraction, classification, and parameter optimization. Primarily, the digital video camera is used to capture the RGB color images and the video is extracted into a set of frames. For improving the image quality and eliminate noise, the frames are processed in three levels namely resizing, augmentation, and min–max based normalization. Besides, MobileNet model is applied as a feature extractor to derive the spatial features that exist in the preprocessed frames. In addition, the extracted spatial features are then fed into the gated recurrent unit (GRU) to extract the temporal dependencies of the human movements. Finally, a group teaching optimization algorithm (GTOA) with stacked autoencoder (SAE) is used as a binary classification model to determine the existence of fall or non-fall events. The GTOA is employed for the parameter optimization of the SAE model in such a way that the detection performance can be enhanced. In order to assess the fall detection performance of the presented VEFED-DL model, a set of simulations take place on the UR fall detection dataset and multiple cameras fall dataset. The experimental outcomes highlighted the superior performance of the presented method over the recent methods.
Highlights
In past decades, the security of elders living alone turned into a growing problem for society [1]
This paper presents a new vision based elderly fall event detection using deep learning (VEFED-DL) model
The advanced study literature and result show that LSTM is an efficient method to solve long term dependency, and the problem of vanishing gradient is alleviated by gating technique.Since the common variant of LSTM, gated recurrent unit (GRU) simplified the gated structure in LSTM cells and utilizes reset gate and upgrade gate for replacing 3 gates in LSTM, where the reset gate defines the novel input data with the prior memory, and the upgrade gate determines the prior information should be saved for the present time step
Summary
The security of elders living alone turned into a growing problem for society [1]. Falling event is a popular and significant risk among elder people since the older persons are deteriorating in loss of balance, physical function, and slower sensory response These falls create loss of mobility, injury, and other health issues. The fall is the main risk for elder person, with substantial physical, financial, and emotional effects It is considered the main health concern for people who live alone. An ambient sensor-based system exploits pressure/vibration devices set up in the floor/bed to examine the vibration and sounds These sensors are inexpensive and do not distract elder people. Vision-based method uses several cameras for detecting falls These cameras are set up in daily environment and provide high data regarding peoples and their events. For examining the fall detection efficiency of the presented VEFED-DL model, a series of experimentation is carried out on the UR fall detection dataset and multiple cameras fall dataset
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
