Multi-Occupancy Fall Detection Using Non-Invasive Thermal Vision Sensor

Abstract

introduction of a new health-care delivery paradigm [3]. Besides, low-cost sensing solutions, whose wireless services coupled with rapid advances in data analysis, have provided the next generation of products to be deployed within living environments. These have the potential to improve the manner where remote health-care support can be provided and are slowly gaining increased acceptance by both users and health-care professionals [4]. From the multitude of health scenarios to consider, detecting falls within the living environment is a relevant challenge with a high impact in terms of both security and safety. Accidental falls can cause serious injury to at-risk individuals, especially for the aging [5]. Within this cohort, falls are the leading cause of hospitalization, injury-related deaths and loss of independence. However, it has been demonstrated that detecting and rapidly responding to falls can reduce the long-term risks associated with falls. Although efforts have been directed towards supporting the detection and management of falls within living environments, a range of issues still exist. From a usability perspective, challenges are faced by the costs of the solution and the perceived issue of intrusiveness when video based cameras are used. From a technical perspective, challenges are faced by levels of accuracy levels and a desire to reduce the numbers of false positives given the implications that these have from a health-care provision perspective. In addition, the studies of fall detection are mainly

Comprehensive Review of Vision-Based Fall Detection Systems

“…Image binarization, as in [ 89 ], is also introduced as a part of the systematic effort to reduce noise during the segmentation process, while some other systems, like the one presented in [ 56 ], pursue image complexity decreasing by transforming video signals from red, green and blue (RGB) to black and white and then applying a median filter, an algorithm which assigns new values to image pixels based on the median of the surrounding ones.…”

“…Binarization is a technique used for background subtraction, especially in infrared (IR) systems, as the one presented in [ 89 ], where the inputs IR signals pixels are assigned two potential values, 0 and 1. All pixels above a certain threshold value are assigned a value 1 (human body temperature dependent), and all others are given a value of 0.…”

“…A similar procedure is followed by the system in [ 89 ], whose ANN mixes layers of CNN, which deliver features maps from the incoming binarized video signal, with layers of radial basis function neural networks (RBFNN), which will be used as a classifier.…”

“…To reduce the complexity of the trees, and therefore, their computational cost, branches are pruned when the relation cost-saving/accuracy loss is satisfactory. This type of classifier is used in [ 87 , 89 ].…”

“…Radial basis function neural networks (RBFNN) are used in the last layer of [ 89 ] to classify the feature vectors coming from previous CNN layers. This ANN is characterized by using radial basis functions as activation functions and yields better generalization capabilities than other architectures, such as Softmax, as it is trained via minimizing the generalized error estimated by a localized-generalization error model (L-GEM).…”