Real-Time Fall Detection Using Mmwave Radar

Li, Wenxuan; Zhang, Dongheng; Li, Yadong; Wu, Zhi; Chen, Jinbo; Dong, Zhen; Hu, Yang; Sun, Quansen; Chen, Yan

doi:10.1109/icassp43922.2022.9747153

Cited by 25 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [19] presented mmFall, a real-time fall-detection system that utilizes millimeter-wave signals and accomplishes remarkable accuracy while maintaining a low computational complexity. They proposed a spatial-temporal processing method for extracting signal variation related to human activity.…”

Section: Fall Detection With Wearable and Body Sensorsmentioning

confidence: 99%

An Interpretable Modular Deep Learning Framework for Video-Based Fall Detection

Dutt,

Gupta,

Goodwin

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Falls are a major risk factor for older adults, increasing morbidity and healthcare costs. Video-based fall-detection systems offer crucial real-time monitoring and assistance. Yet, their deployment faces challenges such as maintaining privacy, reducing false alarms, and providing understandable outputs for healthcare providers. This paper introduces an innovative automated fall-detection framework that includes a Gaussian blur module for privacy preservation, an OpenPose module for precise pose estimation, a short-time Fourier transform (STFT) module to capture frames with significant motion selectively, and a computationally efficient one-dimensional convolutional neural network (1D-CNN) classification module designed to classify these frames. Additionally, integrating a gradient-weighted class activation mapping (GradCAM) module enhances the system’s explainability by visually highlighting the movement of the key points, resulting in classification decisions. Modular flexibility in our system allows customization to meet specific privacy and monitoring needs, enabling the activation or deactivation of modules according to the operational requirements of different healthcare settings. This combination of STFT and 1D-CNN ensures fast and efficient processing, which is essential in healthcare environments where real-time response and accuracy are vital. We validated our approach across multiple datasets, including the Multiple Cameras Fall Dataset (MCFD), the UR fall dataset, and the NTU RGB+D Dataset, which demonstrates high accuracy in detecting falls and provides the interpretability of results.

show abstract

Section: Fall Detection With Wearable and Body Sensorsmentioning

confidence: 99%

An Interpretable Modular Deep Learning Framework for Video-Based Fall Detection

Dutt,

Gupta,

Goodwin

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The drop ratio of the drop-out layer was 0.3. Furthermore, we have tried our best to rebuild the CNN [26], 3DCNN [28], and CNN + LSTM [20] networks from the reference studies. A few parameters, such as convolution kernel size, were adjusted to fit our data format.…”

Section: B Implementation Detailsmentioning

confidence: 99%

“…Compared with the accuracy rate in our previous work, the performance degradation was caused by the expanded data set, which brought a great challenge to adjust handcraft feature extraction to all records. In addition, each RD frame was scaled to a 64×64 image and fed into 3DCNN [28] and CNN + LSTM [20] networks. They obtained 93.5% and 94.2% classification accuracy, respectively.…”

Section: Performance Comparisonmentioning

confidence: 99%

“…Two separate TD spectrums with different temporal resolutions were taken as input to the dual-channel architecture. Moreover, a 3-D convolutional neural network (CNN)-based network was designed to extract the complex features from RD frames and achieved good performance in real-time fall detection [28]. RNN-based methods perform well in processing sequential data streams for considering both current and previous observations [29], [30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sparsity-Based Human Activity Recognition With PointNet Using a Portable FMCW Radar

Ding

Zhang

Chen

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

“…A new long-short-term memory architecture (LSTM) called cerebral LSTM was introduced by [ 27 ] on wearable devices to detect falls. A millimetre wave signal-based real-time fall detection system called mmFall was proposed by [ 28 ]. It achieved high accuracy and low computational complexity by extracting signal fluctuation related to human activity using spatial-temporal processing and developing a light convolutional neural network.…”

Section: Literature Reviewmentioning

confidence: 99%

Synergistic Integration of Skeletal Kinematic Features for Vision-Based Fall Detection

Inturi

Manikandan

Kumar

et al. 2023

Sensors

View full text Add to dashboard Cite

According to the World Health Organisation, falling is a major health problem with potentially fatal implications. Each year, thousands of people die as a result of falls, with seniors making up 80% of these fatalities. The automatic detection of falls may reduce the severity of the consequences. Our study focuses on developing a vision-based fall detection system. Our work proposes a new feature descriptor that results in a new fall detection framework. The body geometry of the subject is analyzed and patterns that help to distinguish falls from non-fall activities are identified in our proposed method. An AlphaPose network is employed to identify 17 keypoints on the human skeleton. Thirteen keypoints are used in our study, and we compute two additional keypoints. These 15 keypoints are divided into five segments, each of which consists of a group of three non-collinear points. These five segments represent the left hand, right hand, left leg, right leg and craniocaudal section. A novel feature descriptor is generated by extracting the distances from the segmented parts, angles within the segmented parts and the angle of inclination for every segmented part. As a result, we may extract three features from each segment, giving us 15 features per frame that preserve spatial information. To capture temporal dynamics, the extracted spatial features are arranged in the temporal sequence. As a result, the feature descriptor in the proposed approach preserves the spatio-temporal dynamics. Thus, a feature descriptor of size [m×15] is formed where m is the number of frames. To recognize fall patterns, machine learning approaches such as decision trees, random forests, and gradient boost are applied to the feature descriptor. Our system was evaluated on the UPfall dataset, which is a benchmark dataset. It has shown very good performance compared to the state-of-the-art approaches.

show abstract

Real-Time Fall Detection Using Mmwave Radar

Cited by 25 publications

References 16 publications

An Interpretable Modular Deep Learning Framework for Video-Based Fall Detection

An Interpretable Modular Deep Learning Framework for Video-Based Fall Detection

Sparsity-Based Human Activity Recognition With PointNet Using a Portable FMCW Radar

Synergistic Integration of Skeletal Kinematic Features for Vision-Based Fall Detection

Contact Info

Product

Resources

About