Multi-Stream Deep Convolutional Network Using High-Level Features Applied to Fall Detection in Video Sequences

Cameiro, Sarah Almeida; Silva, Gabriel Pellegrino da; Leite, Guilherme Vieira; Moreno, Ricardo; Guimarães, Silvio Jamil Ferzoli; Pedrini, Hélio

doi:10.1109/iwssip.2019.8787213

Cited by 24 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Tables I, II and III, we categorized all the systems that work with vision data and with various sensors data. Vision based systems work with the data from RGB and Depth camera of Kinect shown in [63], [64], [80], [81], [98], [100], [107], [108], RGB Cameras introduced in [67], [69], [76], [78], [82], [85], [96], [97], [108]. Sensor based systems work with accelerometer data shown in [70], [72], [74], [77], [79], [99], [102]- [106], gyroscope data depicted in [70], [104], radar data demonstrated in [69], [71], [116], [119].…”

Section: A Discussionmentioning

confidence: 99%

“…The system developed in [84] has also achieved the highest accuracy of 100% using 3D CNN. The systems in [64], [69], [74], [76], [77], [80], [82], [96] have also achieved high levels of accuracy using various deep learning methods. The highest accuracy achieved 99.98% in [64] using CNN with 10-fold crossvalidation, 99.85% in [69] using three CNN based on Alex-Net and SSD-Net, 99.84% in [96] using 3D CNN along with LSTM.…”

Section: A Discussionmentioning

confidence: 99%

“…It is shown that almost all systems have used the key term "Fall detection" for describing their methods and systems. A few number of systems have also used the key term "Fall recognition" [74], [77], [78], [79], [85], [100], [102] and "Fall localization" [69], [73], [76], [80], [83], [85], [97], [100], [118] along with the key term "Fall detection". Hence, detection and recognition can be interchangeably used in terms of fall events.…”

Section: A Discussionmentioning

confidence: 99%

“…The reviewed system achieved a detection rate of 91.5%, while using 5-fold cross-validation. Multi-stream model concept is used by Cameiro et al [76] for fall detection. The system proposes a multi-stream model that takes high-level handcrafted features as input.…”

Section: A Convolutional Neural Network (Cnn) Based Fall Detection Smentioning

confidence: 99%

“…Various datasets have been used in the reviewed systems. Some of them used publicly available dataset such as KTH dataset [85], Uni-MiB SHAR [75], [77], [79] SisFall [70], [77], [79] UMA fall [79], UP-Fall [78], Multicam [78], URFD [64], [65], [73] and [76]. Some of them used simulated datasets generated by trainers.…”

Section: )mentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning Based Systems Developed for Fall Detection: A Review

et al. 2020

View full text Add to dashboard Cite

Accidental falls are a major source of loss of autonomy, deaths, and injuries among the elderly. Accidental falls also have a remarkable impact on the costs of national health systems. Thus, extensive research and development of fall detection and rescue systems are a necessity. Technologies related to fall detection should be reliable and effective to ensure a proper response. This paper provides a comprehensive review on state-of-the-art fall detection technologies considering the most powerful deep learning methodologies. We reviewed the most recent and effective deep learning methods for fall detection and categorized them into three categories: Convolutional Neural Network (CNN) based systems, Long Short-Term Memory (LSTM) based systems, and Auto-encoder based systems. Among the reviewed systems, three dimensional (3D) CNN, CNN with 10-fold cross-validation, LSTM with CNN based systems performed the best in terms of accuracy, sensitivity, specificity, etc. The reviewed systems were compared based on their working principles, used deep learning methods, used datasets, performance metrics, etc. This review is aimed at presenting a summary and comparison of existing state-of-the-art deep learning based fall detection systems to facilitate future development in this field.

show abstract