A Customized Human Fall Detection System Using Omni-Camera Images and Personal Information

Miaou, Shaou-Gang; Sung, Pei-Hsu; Huang, Chun‐Sheng

doi:10.1109/ddhh.2006.1624792

Cited by 186 publications

(90 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mubashir et al [3] tracked the person's head to improve their base results using a multiframe Gaussian classifier, which was fed with the direction of the principal component and the variance ratio of the silhouette. Another common technique consists in computing the bounding boxes of the objects to determine if they contain a person and then detect the fall by means of features extracted from it (see, for instance, [20,21]). Following a similar strategy, Vishwakarma et al [22] worked with bounding boxes to compute the aspect ratio, horizontal and vertical gradients of an object, and fall angle and fed them into a GMM to obtain a final answer.…”

Section: Related Workmentioning

confidence: 99%

Vision-Based Fall Detection with Convolutional Neural Networks

Núñez-Marcos

Azkune

Arganda‐Carreras

2017

Wireless Communications and Mobile Computing

220

125

View full text Add to dashboard Cite

One of the biggest challenges in modern societies is the improvement of healthy aging and the support to older persons in their daily activities. In particular, given its social and economic impact, the automatic detection of falls has attracted considerable attention in the computer vision and pattern recognition communities. Although the approaches based on wearable sensors have provided high detection rates, some of the potential users are reluctant to wear them and thus their use is not yet normalized. As a consequence, alternative approaches such as vision-based methods have emerged. We firmly believe that the irruption of the Smart Environments and the Internet of Things paradigms, together with the increasing number of cameras in our daily environment, forms an optimal context for vision-based systems. Consequently, here we propose a vision-based solution using Convolutional Neural Networks to decide if a sequence of frames contains a person falling. To model the video motion and make the system scenario independent, we use optical flow images as input to the networks followed by a novel three-step training phase. Furthermore, our method is evaluated in three public datasets achieving the state-of-the-art results in all three of them.

show abstract

Section: Related Workmentioning

confidence: 99%

Vision-Based Fall Detection with Convolutional Neural Networks

Núñez-Marcos

Azkune

Arganda‐Carreras

2017

Wireless Communications and Mobile Computing

220

125

View full text Add to dashboard Cite

show abstract

“…The authors use k-nearest neighbor classifier to categorize the body posture and a fall is decided based on the time difference of event transitions. Several other approaches are also employed such as Rule-based techniques [21], Bayesian filtering [22], Hidden Markov Models [23], Threshold techniques [24] and Fuzzy Logic [25]. Among these decision and extraction techniques, none of them shows outstanding performance to the others and no appropriate comparison has been done yet.…”

Section: Related Workmentioning

confidence: 99%

“…Most of them utilize the common approach of extracting the personal features and comparing with the model to determine a fallen event. Features which could be collected are the ratio of weight and height [15], changes in light and illumination [16], direction of main axis of the body [17], skin color to detect the body region [18]. These features are then analyzed to distinguish between normal behaviors and fall events by different techniques.…”

Section: Related Workmentioning

confidence: 99%

Automatic Fall Detection using Smartphone Acceleration Sensor

Dang¹,

Truong²,

Dang³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-In this paper, we describe our work on developing an automatic fall detection technique using smart phone. Fall is detected based on analyzing acceleration patterns generated during various activities. An additional long lie detection algorithm is used to improve fall detection rate while keeping false positive rate at an acceptable value. An application prototype is implemented on Android operating system and is used to evaluate the proposed technique performance. Experiment results show the potential of using this app for fall detection. However, more realistic experiment setting is needed to make this technique suitable for use in real life situations.

show abstract

“…Here comes the importance of designing and implementing an automatic Fall Detection System that detects the fall of unattended older persons and sends an alarm message to the concerned caregivers, to provide the needed help in the shortest delay possible. Fall detection systems can be classified into three main approaches [4]: (1) Computer vision and image processing based approach, in which the movement of the person is monitored in real time through a video capturing system and some algorithms are applied to recognize the posture of the person [5] [16]. In each of the above mentioned approaches, different types of sensing modules, decision making modules, and alarm modules are used.…”

Section: Related Workmentioning

confidence: 99%

RAFDS: Remote Abnormality and Fall Detection System for Assisting Older Persons

Ismail¹,

Kallel²,

Ismail³

2015

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:One of the main problems facing the public health is the injury that happens due to older persons falling, as these injuries can be fatal for them. Fast and proper medical interventions are crucial to reduce the serious consequences on their health. In this paper, a system is designed to continuously monitor vital signs and motion of older persons, and automatically detects incidents of abnormal vital signs as well as the fall of unattended older persons, and, accordingly, sends an alarm message to the concerned caregivers, to provide the needed help in the shortest delay possible. The proposed system is composed of three major modules; firstly the sensing module (SM), which continuously measures the acceleration of the monitored person, as well as vital signs of the monitored persons, such as the temperature and the heart pulse rate. Secondly, the decision making module (DMM) which is a processing element that receives the sensing signals from the sensors used in SM, analyzes them, then makes a decision if an abnormality or a fall is detected or not. Finally, if the DMM detects a fall, it sends this decision signal to the alarm module (AM), which sends SMS messages to the concerned caregivers, whose cell phone numbers, are pre-configured in the AM.

show abstract

A Customized Human Fall Detection System Using Omni-Camera Images and Personal Information

Cited by 186 publications

References 6 publications

Vision-Based Fall Detection with Convolutional Neural Networks

Vision-Based Fall Detection with Convolutional Neural Networks

Automatic Fall Detection using Smartphone Acceleration Sensor

RAFDS: Remote Abnormality and Fall Detection System for Assisting Older Persons

Contact Info

Product

Resources

About