The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Enhancing elderly care: Efficient and reliable real-time fall detection algorithm
Open accessAbstract
Background and Objective: Falls pose a significant risk to public health, especially for the elderly population, and could potentially result in severe injuries or even death. A reliable fall detection system is urgently needed to recognise and promptly alert to falls effectively. A vision-based fall detection system has the advantage of being non-invasive and affordable compared with another popular approach using wearable sensors. Nevertheless, the present challenge lies in the algorithm's limited on-device operating speed due to extremely high computational demands, and the high computational demands are usually essential to improve the performance for the complex scene. Therefore, it is crucial to address the above challenge in computational power and complex scenes. Methods: This article presents the implementation of a real-time fall detection algorithm with low computational costs using a single webcam. The suggested method optimises precision and efficiency by synthesising the strengths of background subtraction and the human pose estimation model BlazePose. The biomechanical features, derived from body key points identified by BlazePose, are utilised in a random forest model for classifying fall events. Results: The proposed algorithm achieves 89.99% accuracy and 29.7 FPS with a laptop CPU on the UR Fall Detection dataset and the Le2i Fall Detection dataset. The algorithm shows great generalisation and robustness in different scenarios. Conclusion: Due to the low computational power of the system, the findings also suggest the potential for implementing the system in small-scale medical monitoring equipment, which maximises its practical value in digital health.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“An AR>1.0 typically indicated a transition to a lying state, distinguishing falls from daily activities like sitting [14].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Given the inherent class imbalance (pre-test n= 41,223 vs. post-test n= 7969), representative of real-world scenarios where “correct” falls are less frequent than untrained ones, we prioritised metrics robust to skewness, specifically the F1-Score and the Area Under the Receiver Operating Characteristic Curve (AUC) [14].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Special emphasis was placed on Sensitivity (Recall), as minimizing False Negatives (labeling a dangerous fall as safe) is critical in injury prevention scenarios [14].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
The cited source says what the claim attributes to it.
In the citing paper
“Unlike binary fall detection systems that focus solely on identifying the occurrence of a fall event [14], this analysis aims to quantify the learning effect embedded in the movement patterns.”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
The cited source says what the claim attributes to it.
In the citing paper
“For instance, Wang et al. (2024) reported an accuracy of 89.99% using Random Forest with BlazePose features [14], and Kong et al. (2025) achieved an F1-score of 91.4% using an SVM on geometric features [20].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
The cited source says what the claim attributes to it.
In the citing paper
“Our proposed framework compares favourably with recent vision-based benchmarks. For instance, Wang et al. (2024) reported an accuracy of 89.99% using Random Forest with BlazePose features [14], and Kong et al. (2025) achieved an F1-score of 91.4% using an SVM on geometric features [20].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This “White-Box” approach is essential for validating the pedagogical effectiveness of the Safe Fall programme [14].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [14]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
A Threshold Selection Method from Gray-Level Histograms
Otsu, N. (1979) · IEEE Transactions on Systems, Man and Cybernetics · doi:10.1109/tsmc.1979.4310076 · Cited by 44,708
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., & Sheikh, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2929257 · Cited by 5,536
Gomarasca, M. A. (2009) · Springer eBooks · doi:10.1007/978-1-4020-9014-1_8 · Cited by 2,629
Efficient adaptive density estimation per image pixel for the task of background subtraction
Živković, Z., & van der Heijden, F. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.11.005 · Cited by 1,583
Prevention of falls and consequent injuries in elderly people
Kannus, P., Sievänen, H. T., Palvanen, M., Järvinen, T. L. N., & Parkkari, J. P. (2005) · The Lancet · doi:10.1016/s0140-6736(05)67604-0 · Cited by 1,128
Elderly Fall Detection Systems: A Literature Survey
Wang, X., Ellul, J., & Azzopardi, G. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.00071 · Cited by 410
Charfi, I., Mitéran, J., Dubois, J., Atri, M., & Tourki, R. (2013) · Journal of Electronic Imaging · doi:10.1117/1.jei.22.4.041106 · Cited by 217
Distinguishing fall activities from normal activities by velocity characteristics
Wu, G. (2000) · Journal of Biomechanics · doi:10.1016/s0021-9290(00)00117-2 · Cited by 192
Flagged first, then by citations
Research works printed but not linked: 1
- Bazarevsky V, 2020, BlazePose: on-device real-time body pose tracking
Cited by
Sorted by citations
DelCastillo-Andrés, O., Fernández-García, R., Pastor-Vicedo, J. C., Lira, M. A., Campos-Mesa, M. C., Castañeda-Vázquez, C., Genovesi, E., Krstulović, S., Kuvačić, G., Morvay-Sey, K., et al. (2026) · Sensors · doi:10.3390/s26082491 · Cited by 1
“An AR > 1.0 typically indicated a transition to a lying state, distinguishing falls from daily activities like sitting [14].”
Influential
Metadata
- Authors
- Wang, Y., & Deng, T.
- Affiliations
- University of Sheffield (GB)
- Corresponding author
- Deng, Tiantai
- Venue
- DIGITAL HEALTH
- Publisher
- SAGE Publications
- Published
- 2024-01
- Volume
- 10
- Pages
- 20552076241233690-20552076241233690
- ISSN
- 2055-2076 (ISSN-L)
- PMC
- PMC10880526
- OpenAlex
- W4391975041
- Cited by
- 28
- References
- 21
- Citations by year
- 2026: 8 · 2025: 15 · 2024: 5
- FWCI
- 3.91
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Digital Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- University of Sheffield
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- fall detection, elderly care, real-time fall detection, background subtraction, human pose estimation, BlazePose, biomechanical features, random forest classification, low computational cost, webcam-based monitoring
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
