Human Fall Detection in Surveillance Videos Using Fall Motion Vector Modeling

Vishnu, Chalavadi; Datla, Rajeshreddy; Roy, Debaditya; Babu, Sobhan; Mohan, C. Krishna

doi:10.1109/jsen.2021.3082180

Cited by 61 publications

(18 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The maximum work for fall detection using DL have been done using CNN followed by hybrid, LSTM, Auto-encoder and MLP as shown in Figure 20. These DL based Classification of papers based on the CNN modle used CNN [39,41,44,20,52,45,54,59,61,63,64,65,66,67,68,8,69,71,73,74,76,77,78,79,80,81,82,84,87,88,89,90,91,36,92,93,94,95,99,100,101,102,103,104,107,105,108,106] LSTM [117,…”

Section: Discussion On Limitations and Future Scopementioning

confidence: 99%

See 1 more Smart Citation

Vision-based Human Fall Detection Systems using Deep Learning: A Review

Alam¹,

Sufian²,

Dutta³

et al. 2022

Preprint

View full text Add to dashboard Cite

Human fall is one of the very critical health issues, especially for elders and disabled people living alone. The number of elder populations is increasing steadily worldwide. Therefore, human fall detection is becoming an effective technique for assistive living for those people. For assistive living, deep learning and computer vision have been used largely. In this review article, we discuss deep learning (DL)-based state-of-thearts non-intrusive (vision-based) fall detection techniques. We also present a survey on fall detection benchmark datasets. For a clear understanding, we briefly discuss different metrics which are used to evaluate the performance of the fall detection systems. This article also gives a future direction on vision-based human fall detection techniques.

show abstract

Section: Discussion On Limitations and Future Scopementioning

confidence: 99%

“…Data augmentation was used by changing the spatial, illumination, and temporal properties. Vishnu et al (2021) [104] proposed a fall motion vector based fall detection method using 3D CNN. A pre-trained ResNet-101 was used.…”

Section: Cnn Based Techniquesmentioning

confidence: 99%

Vision-based Human Fall Detection Systems using Deep Learning: A Review

Alam¹,

Sufian²,

Dutta³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The detection was carried out by a continuous screening for the pre-defined acceleration threshold, followed by classification using a logistic regression model pre-trained in a dataset of simulated actions of falling. Vishnu et al [5] developed a high-dimensional representation of falls and non-falls based on a fall motion mixture model that implicitly captures the motion attributes of each act. A low dimensional representation containing the attributes of abnormal actions for a specific video is extracted by performing factor analysis on the model.…”

Section: Traditional Methodsmentioning

confidence: 99%

“…The need for improved techniques of autonomous detection is gaining more and more focus, mainly because of enormous amounts of surveillance data being generated and the impracticality of its manual monitoring because of the human toil involved. Several traditional (e.g., [3][4][5]) as well as deep learning-based methods (e.g., [6][7][8]) have focused on the problem. Abnormal events detection encompasses two types of video scenes: crowded and uncrowded [9].…”

Section: Introductionmentioning

confidence: 99%

LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection

Mehmood

2021

Sensors

View full text Add to dashboard Cite

The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation.

show abstract

“…In current literature, much research is performed in developing algorithms based on cameras [6], wearables [7], RF based [8] detection or a fusion of different data streams [9], [10]. Many of these algorithms are based on a type of Machine Learning (ML).…”

Section: Introductionmentioning

confidence: 99%

Fall Detection and Warning System for Nursing Homes based on Bluetooth Low Energy

Raeve

Nzamuye

Claus

et al. 2022

2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)

View full text Add to dashboard Cite

Fall accidents are a frequent problem with the elderly and lead to severe injuries and/or could have a lethal ending. To prevent these potential deaths the nursing personnel visits the elderly on a regular basis. This has an enormous influence on the mental and physical capabilities of the nursing personnel. In combination with the ever-growing presence of Internet of Things (IoT) applications, this paper proposes a low-power wireless fall detection and warning system based on Bluetooth Low Energy (BLE). The aim of the system is to lower the workload of the nursing personnel and prevent elderly from dying from hypothermia. The system consists of a patient wearable (P) monitoring the movement of the elderly, a Detection Node (DN) scanning the room of the elderly to pinpoint the position of the fallen elderly, multiple Network Nodes (NNs) in the hallways sending the alert messages to the closest caretaker wearing a Caretaker Node (CN). This node visualizes all vital parameters, so the nursing personnel can help in the fastest way possible. A proof-of-concept is proposed in this paper, together with measurements and power analysis.

show abstract

Human Fall Detection in Surveillance Videos Using Fall Motion Vector Modeling

Cited by 61 publications

References 41 publications

Vision-based Human Fall Detection Systems using Deep Learning: A Review

Vision-based Human Fall Detection Systems using Deep Learning: A Review

LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection

Fall Detection and Warning System for Nursing Homes based on Bluetooth Low Energy

Contact Info

Product

Resources

About