Fall Detection of Elderly People Using the Manifold of Positive Semidefinite Matrices

Alaoui, Abdessamad Youssfi; Tabii, Youness; Thami, Rachid Oulad Haj; Daoudi, Mohamed; Pala, Pietro

doi:10.3390/jimaging7070109

Cited by 17 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yolo (v1, v2, v3, v4 and v5) [102,103,105,113,117] RGB Images [102], Thermal Images [103,105,113,117] Pedestrian detection [102][103][104][105][106][107][108][109][110][111][112][113][114]117,118], falling elderly people [118] Tiny (v3,l3, v2) [103,105,113] Thermal Images [103,105,113] Fast R-CNN [104,106] RGB Images [106], Thermal Images [104,106] HOG [107,110,113] RGB Images [110], Thermal Images [107,110,113] SVM [107][108][109][110]...…”

Section: Data Type Purposementioning

confidence: 99%

The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines

Imam

Bäına

Tabii

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Underground mining operations present critical safety hazards due to limited visibility and blind areas, which can lead to collisions between mobile machines and vehicles or persons, causing accidents and fatalities. This paper aims to survey the existing literature on anti-collision systems based on computer vision for pedestrian detection in underground mines, categorize them based on the types of sensors used, and evaluate their effectiveness in deep underground environments. A systematic review of the literature was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify relevant research work on anti-collision systems for underground mining. The selected studies were analyzed and categorized based on the types of sensors used and their advantages and limitations in deep underground environments. This study provides an overview of the anti-collision systems used in underground mining, including cameras and lidar sensors, and their effectiveness in detecting pedestrians in deep underground environments. Anti-collision systems based on computer vision are effective in reducing accidents and fatalities in underground mining operations. However, their performance is influenced by factors, such as lighting conditions, sensor placement, and sensor range. The findings of this study have significant implications for the mining industry and could help improve safety in underground mining operations. This review and analysis of existing anti-collision systems can guide mining companies in selecting the most suitable system for their specific needs, ultimately reducing the risk of accidents and fatalities.

show abstract

Section: Data Type Purposementioning

confidence: 99%

The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines

Imam

Bäına

Tabii

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The attention mechanism added by our method is more novel and efficient than the attention module of Lightweight ST-GCN, with a 2.6% increase in test accuracy, a 5.28% increase in sensitivity, and a 4.3% increase in specificity. The literature [24] detects human skeleton information used V2V-PoseNet and then used a dynamic time warping (DTW) algorithm to calculate the variability of action execution speed between adjacent sequences and thus classify whether they have fallen or not. The method is relatively simple, but it is easy to misjudge movements with large speed differences between adjacent frames, such as squatting and bending, which leads to a low accuracy rate.…”

Section: Dataset Evaluation Experimentsmentioning

confidence: 99%

Worker Abnormal Behavior Recognition Based on Spatio-Temporal Graph Convolution and Attention Model

Zhang

Han

et al. 2023

Electronics

View full text Add to dashboard Cite

In response to the problem where many existing research models only consider acquiring the temporal information between sequences of continuous skeletons and in response to the lack of the ability to model spatial information, this study proposes a model for recognizing worker falls and lays out abnormal behaviors based on human skeletal key points and a spatio-temporal graph convolutional network (ST-GCN). Skeleton extraction of the human body in video sequences was performed using Alphapose. To resolve the problem of graph convolutional networks not being effective enough for skeletal key points feature aggregation, we propose an NAM-STGCN model that incorporates a normalized attention mechanism. By using the activation function PReLU to optimize the model structure, the improved ST-GCN model can more effectively extract skeletal key points action features in the spatio-temporal dimension for the purposes of abnormal behavior recognition. The experimental results show that our optimized model achieves a 96.72% accuracy for recognition on the self-built dataset, which is 4.92% better than the original model; the model loss value converges below 0.2. Tests were performed on the KTH and Le2i datasets, which are both better than typical classification recognition networks. The model can precisely identify abnormal human behaviors, facilitating the detection of abnormalities and rescue in a timely manner and offering novel ideas for smart site construction.

show abstract

“…The human body centroids measure the angle between the human body and the floor level. When the angle is smaller than the defined thresholds, the fall events are detected, and several other techniques have been proposed [32,33]. However, in all the abovementioned cases, particular attention has not been devoted to addressing fall-relevant injuries.…”

Section: Related Workmentioning

confidence: 99%

A Cost-Effective Fall-Detection Framework for the Elderly Using Sensor-Based Technologies

et al. 2023

View full text Add to dashboard Cite

Falls are critical events among the elderly living alone in their rooms and can have intense consequences, such as the elderly person being left to lie for a long time after the fall. Elderly falling is one of the serious healthcare issues that have been investigated by researchers for over a decade, and several techniques and methods have been proposed to detect fall events. To overcome and mitigate elderly fall issues, such as being left to lie for a long time after a fall, this project presents a low-cost, motion-based technique for detecting all events. In this study, we used IRA-E700ST0 pyroelectric infrared sensors (PIR) that are mounted on walls around or near the patient bed in a horizontal field of view to detect regular motions and patient fall events; we used PIR sensors along with Arduino Uno to detect patient falls and save the collected data in Arduino SD for classification. For data collection, 20 persons contributed as patients performing fall events. When a patient or elderly person falls, a signal of different intensity (high) is produced, which certainly differs from the signals generated due to normal motion. A set of parameters was extracted from the signals generated by the PIR sensors during falling and regular motions to build the dataset. When the system detects a fall event and turns on the green signal, an alarm is generated, and a message is sent to inform the family members or caregivers of the individual. Furthermore, we classified the elderly fall event dataset using five machine learning (ML) classifiers, namely: random forest (RF), decision tree (DT), support vector machine (SVM), naïve Bayes (NB), and AdaBoost (AB). Our result reveals that the RF and AB algorithms achieved almost 99% accuracy in elderly fall-d\detection.

show abstract

Fall Detection of Elderly People Using the Manifold of Positive Semidefinite Matrices

Cited by 17 publications

References 51 publications

The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines

The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines

Worker Abnormal Behavior Recognition Based on Spatio-Temporal Graph Convolution and Attention Model

A Cost-Effective Fall-Detection Framework for the Elderly Using Sensor-Based Technologies

Contact Info

Product

Resources

About