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

Chen, Yong; Li, Weitong; Wang, Lu; Hu, Jiajia; Ye, Mingbin

doi:10.1109/access.2020.3021795

Cited by 61 publications

(35 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4. A fall detection method using attention guided Bi-Directional LSTM (called Bi-LSTM-FD method for short) [32]. After using Mask R-CNN to extract moving objects in noisy backgrounds, this method employs an attention guided Bi-directional LSTM for fall detection.…”

Section: Resultsmentioning

confidence: 99%

“…Haben proposed an image-based fall detection method using deep convolutional neural network (DCNN) [31]. In [32], Mask-RCNN involving ResNet-50 was used as a human detector and an attention guided Bi-directional LSTM was presented to achieve fall detection. In [33], Yolo v3, a deep network, was utilized to obtain bounding box and VGG-16 together with LSTM model was adopted for fall event discrimination.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vision-Based Fall Detection Using Dense Block With Multi-Channel Convolutional Fusion Strategy

Han

2021

IEEE Access

View full text Add to dashboard Cite

Fall detection has become a hot issue in the field of video surveillance recently. Different from most traditional vision-based methods relying on hand-crafted features, fall detection methods based on deep learning technology can automatically mine features to detect fall events due to the powerful ability of deep learning in data analysis, and hence have received much more attention in recent years. However, information loss has become a problem that cannot be ignored, especially for the neural networks with deep layers, because loss of information will affect representativeness of features and further influence the performance of fall detection. To solve the abovementioned problem, we propose a fall detection method based on dense block with a multi-channel convolutional fusion (MCCF) strategy. In this method, MCCF-DenseBlock, a densely connected network structure, is proposed to fully extract information with its densely connected layers, and to avoid network overloading by breaking dense connections appropriately, and especially to reduce data redundancy and numerous parameters in the network via the MCCF strategy fusing its grouped features. Besides, an improved transition layer is presented to further lessen data accumulation by using a multi-level downsampling structure. Experimental results demonstrate that, the proposed method can provide accurate fall detection results (satisfactory F-score of 0.973 on the UR Fall Dataset) and outperforms several state-of-the-art methods. INDEX TERMS Fall detection, deep learning, multi-channel convolutional fusion (MCCF), MCCF-DenseBlock.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Vision-Based Fall Detection Using Dense Block With Multi-Channel Convolutional Fusion Strategy

Han

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…While the first layer has recurrent connections, in the second one, connections are flipped and passed backward through the activation function signal. This topology is incorporated in [ 104 ], where Bi-LSTM layers are stacked over CNN layers used to segment incoming images.…”

Section: Discussionmentioning

confidence: 99%

Comprehensive Review of Vision-Based Fall Detection Systems

Gutiérrez

Rodríguez²,

Martín

2021

Sensors

View full text Add to dashboard Cite

Vision-based fall detection systems have experienced fast development over the last years. To determine the course of its evolution and help new researchers, the main audience of this paper, a comprehensive revision of all published articles in the main scientific databases regarding this area during the last five years has been made. After a selection process, detailed in the Materials and Methods Section, eighty-one systems were thoroughly reviewed. Their characterization and classification techniques were analyzed and categorized. Their performance data were also studied, and comparisons were made to determine which classifying methods best work in this field. The evolution of artificial vision technology, very positively influenced by the incorporation of artificial neural networks, has allowed fall characterization to become more resistant to noise resultant from illumination phenomena or occlusion. The classification has also taken advantage of these networks, and the field starts using robots to make these systems mobile. However, datasets used to train them lack real-world data, raising doubts about their performances facing real elderly falls. In addition, there is no evidence of strong connections between the elderly and the communities of researchers.

show abstract

“…Moreover, A vision-based human fall detection model is proposed by Chen et al [ 7 ] in the case of complex background. They perform the mask R-CNN method to extract the object from a noisy background.…”

Section: Related Workmentioning

confidence: 99%

“…To identify fall at right, in recent years various methods are proposed using advanced devices like wearable sensors, accelerometers, gyroscope, magnetometers and so on. However, this is not an effective solution since it is impractical to wear a device for a long time [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

Classification of Indoor Human Fall Events Using Deep Learning

Sultana

Deb

Dhar

et al. 2021

Entropy

View full text Add to dashboard Cite

Human fall identification can play a significant role in generating sensor based alarm systems, assisting physical therapists not only to reduce after fall effects but also to save human lives. Usually, elderly people suffer from various kinds of diseases and fall action is a very frequently occurring circumstance at this time for them. In this regard, this paper represents an architecture to classify fall events from others indoor natural activities of human beings. Video frame generator is applied to extract frame from video clips. Initially, a two dimensional convolutional neural network (2DCNN) model is proposed to extract features from video frames. Afterward, gated recurrent unit (GRU) network finds the temporal dependency of human movement. Binary cross-entropy loss function is calculated to update the attributes of the network like weights, learning rate to minimize the losses. Finally, sigmoid classifier is used for binary classification to detect human fall events. Experimental result shows that the proposed model obtains an accuracy of 99%, which outperforms other state-of-the-art models.

show abstract

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

Cited by 61 publications

References 62 publications

Vision-Based Fall Detection Using Dense Block With Multi-Channel Convolutional Fusion Strategy

Vision-Based Fall Detection Using Dense Block With Multi-Channel Convolutional Fusion Strategy

Comprehensive Review of Vision-Based Fall Detection Systems

Classification of Indoor Human Fall Events Using Deep Learning

Contact Info

Product

Resources

About