Human fall detection based on adaptive background mixture model and HMM

Tra, Khue; Tuấn, Phạm Minh

doi:10.1109/atc.2013.6698085

Cited by 19 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of computer vision and image processing technology, computer vision-based fall detection [46][47][48][49][50][51][52] has become an important method, as the systems are less invasive to elderly and higher precision and robustness, in the period of 2003-2018. The algorithm includes background subtraction and feature classification.…”

Section: Related Work and Contributionmentioning

confidence: 99%

“…The shape deformation is then quantified from these silhouettes, and the classification is based on the shape deformation using a Gaussian mixture model. An adaptive background Gaussian mixture model (GMM) is used to obtain the moving object in [51], and an ellipse shape is built from the moving object for body modeling. Several features are then extracted from the ellipse model.…”

Section: Related Work and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-Directional LSTM

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Fall event, as one of the greatest risks to the elderly, its detection has been a hot research issue in the solitary scene in recent years. Nevertheless, most current researches are conducted in the ideal environments, without considering the challenge of complex background in real situation. Therefore, this paper aims to detect fall event detection in complex background based on visual data. Different from most conventional background subtraction methods which depend on background modeling, Mask R-CNN method is first used to accurately extract the moving objects in the noise background. Then, an attention guided Bi-directional LSTM model is proposed for the final fall event detection. To demonstrate the efficiency, the proposed method is verified in the public dataset and self-build dataset. Evaluation of the algorithm performances in comparison with other stateof-the-art methods indicates that the proposed design is accurate and robust, which means it is suitable for the task of fall event detection in complex situation.

show abstract

Section: Related Work and Contributionmentioning

confidence: 99%

Section: Related Work and Contributionmentioning

confidence: 99%

Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-Directional LSTM

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…From the set of costs ( , ) between all pairs of points, the best matched-points can find by using the Hungarian algorithm for minimizing the total matching cost ( ) given a transition ( ) shown in equation (4).…”

Section: B Matching With Shape Contextmentioning

confidence: 99%

“…A 3D depth-sensing camera [3], it can give a good result to detect fall, but the installed camera on side view will be obstructed by the object. Next, human shape estimate by fit ellipse and Motion History Image (MHI) [4] classified by Hidden Markov Models (HMM) give a good result. However, MHI feature is difficult to detection falls with occlusion.…”

Section: Introductionmentioning

confidence: 99%

Human Fall Detection using Maximum Euclidean Distance and Ellipse Approximation

2016

IJAMAE

View full text Add to dashboard Cite

Abstract-The population of senior citizens is continuously increasing, and most of them are living alone at home. The fall is main cause to make severe injury or mortality. The fall detection systems turn into equipment to help elderly rapidly. A technology to detect fall based on vision systems offers a new promising solution to analyze human behavior and detect fall events. In this paper, we propose a new method to detect falls in a video sequence. In our proposed system, the Maximum Euclidean Distance was used for human motion analysis. Then the fall posture of human is detected by using the approximated ellipse method. Our algorithm provides promising results on video sequences of daily activities taken by IP camera installed on a high position like bird's eye view and simulated falls with occlusions.

show abstract

“…Pattern recognition methods comprise Artificial Intelligence, rule-based and machine learning based algorithms that typically base on diverse classification techniques such as Neural Networks and perceptrons [ 36 , 167 ], instance based learning [ 173 ], fuzzy logic systems [ 33 ], Gaussian Mixture Model [ 174 ], decision trees [ 67 ], Naïve Bayes classifier [ 175 ], Hidden Markov Models [ 62 , 66 ], k-Nearest Neighbor [ 41 ], Fisher’s Discriminant Ratio [ 148 ], Hjorth parameters [ 176 ], k-mean [ 177 ] or Support Vector Machine [ 166 ].…”

Section: Analysis Of the Fall Detection Algorithmsmentioning

confidence: 99%

Analysis of Android Device-Based Solutions for Fall Detection

Casilari

Luque

Morón

2015

Sensors

View full text Add to dashboard Cite

Falls are a major cause of health and psychological problems as well as hospitalization costs among older adults. Thus, the investigation on automatic Fall Detection Systems (FDSs) has received special attention from the research community during the last decade. In this area, the widespread popularity, decreasing price, computing capabilities, built-in sensors and multiplicity of wireless interfaces of Android-based devices (especially smartphones) have fostered the adoption of this technology to deploy wearable and inexpensive architectures for fall detection. This paper presents a critical and thorough analysis of those existing fall detection systems that are based on Android devices. The review systematically classifies and compares the proposals of the literature taking into account different criteria such as the system architecture, the employed sensors, the detection algorithm or the response in case of a fall alarms. The study emphasizes the analysis of the evaluation methods that are employed to assess the effectiveness of the detection process. The review reveals the complete lack of a reference framework to validate and compare the proposals. In addition, the study also shows that most research works do not evaluate the actual applicability of the Android devices (with limited battery and computing resources) to fall detection solutions.

show abstract

Human fall detection based on adaptive background mixture model and HMM

Cited by 19 publications

References 8 publications

Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-Directional LSTM

Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-Directional LSTM

Human Fall Detection using Maximum Euclidean Distance and Ellipse Approximation

Analysis of Android Device-Based Solutions for Fall Detection

Contact Info

Product

Resources

About