Three-Stream Convolutional Neural Network for Human Fall Detection

Leite, Guilherme Vieira; Silva, Gabriel Pellegrino da; Pedrini, Hélio

doi:10.1007/978-981-15-6759-9_3

Cited by 6 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 25 ], the authors proposed a method capable of detecting human falls in video sequences using multi-channel CNN and SVM. The results are competitive with those obtained by the state of the art on the UR-Fall dataset.…”

Section: Fall Detection Datasets and Related Workmentioning

confidence: 99%

Human Activity Recognition by Sequences of Skeleton Features

Ramirez

Velastín

Aguayo

et al. 2022

Sensors

View full text Add to dashboard Cite

In recent years, much effort has been devoted to the development of applications capable of detecting different types of human activity. In this field, fall detection is particularly relevant, especially for the elderly. On the one hand, some applications use wearable sensors that are integrated into cell phones, necklaces or smart bracelets to detect sudden movements of the person wearing the device. The main drawback of these types of systems is that these devices must be placed on a person’s body. This is a major drawback because they can be uncomfortable, in addition to the fact that these systems cannot be implemented in open spaces and with unfamiliar people. In contrast, other approaches perform activity recognition from video camera images, which have many advantages over the previous ones since the user is not required to wear the sensors. As a result, these applications can be implemented in open spaces and with unknown people. This paper presents a vision-based algorithm for activity recognition. The main contribution of this work is to use human skeleton pose estimation as a feature extraction method for activity detection in video camera images. The use of this method allows the detection of multiple people’s activities in the same scene. The algorithm is also capable of classifying multi-frame activities, precisely for those that need more than one frame to be detected. The method is evaluated with the public UP-FALL dataset and compared to similar algorithms using the same dataset.

show abstract

Section: Fall Detection Datasets and Related Workmentioning

confidence: 99%

Human Activity Recognition by Sequences of Skeleton Features

Ramirez

Velastín

Aguayo

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…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%

“…Leite et al (2021) [102] introduced three-streamed 3D CNN network-based fall detection system. A pre-trained network on ImageNet was used for each stream.…”

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

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

“…In [13], the authors combined data from two cameras, and they extracted the relative motion between each two consecutive frames from both sensors to classify the overall activity. In the study conducted in [14], a fusion approach was utilized to detect falls in videos. Three distinct types of features, namely optical flow, human pose, and visual rhythm, were extracted from the same video.…”

Section: Related Workmentioning

confidence: 99%

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Mobsite,

Alaoui,

Boulmalf

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In the realm of senior care, falls remain the primary cause of hospitalization and mortality. Early detection can facilitate timely medical interventions and mitigate the associated risks. Hence, it is beneficial to set up a mechanism to identify and track such incidents. While wearable sensors are commonly used for this purpose, they may not be feasible for daily use. In contrast, surveillance cameras provide an unobtrusive and convenient monitoring solution. Despite the intricate nature of video frames, employing deep learning techniques for human recognition can enhance the performance of such systems. In our approach, activity classification is triggered only when a person is detected in the environment. We then process the extracted Global History of Motion (GHM) images with our Lightweight Deep Neural Network (LDNN). Additionally, we employ a dilated Convolution Long Short Term Memory (ConvLSTM) coupled with our LDNN to analyze the extracted sequence of monocular depth frames. Ultimately, the decision is made based on the combined information from both streams. Empirical results demonstrate the good performance of our fall detection system on the UP-Fall and UR datasets compared to the state-of-the-art. In terms of person classification, the Xception network achieved an F1-score of 98.46% on a sub-dataset derived from the COCO dataset, and 100% on the UP-Fall dataset.

show abstract

Three-Stream Convolutional Neural Network for Human Fall Detection

Cited by 6 publications

References 45 publications

Human Activity Recognition by Sequences of Skeleton Features

Human Activity Recognition by Sequences of Skeleton Features

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

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Contact Info

Product

Resources

About