{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T19:19:13Z","timestamp":1792523953641,"version":"4.5.0"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Falls pose a significant health risk for elderly populations, necessitating advanced monitoring technologies. This study introduces a novel two-stage fall detection system that combines computer vision and machine learning to accurately identify fall events. The system uses the YOLOv11 object detection model to track individuals and estimate their body pose by identifying 17 key body points across video frames. The proposed approach extracts nine critical geometric features, including the center of mass and various body angles. These features are used to train a support vector machine (SVM) model for binary classification, distinguishing between standing and lying with high precision. The system\u2019s temporal validation method analyzes sequential frame changes, ensuring robust fall detection. Experimental results, evaluated on the University of Rzeszow Fall Detection (URFD) dataset and the Multiple Cameras Fall Dataset (MCFD), demonstrate exceptional performance, achieving 88.8% precision, 94.1% recall, an F1-score of 91.4%, and a specificity of 95.6%. The method outperforms existing approaches by effectively capturing complex geometric changes during fall events. The system is applicable to smart homes, wearable devices, and healthcare monitoring platforms, offering a scalable, reliable, and efficient solution to enhance safety and independence for elderly individuals, thereby contributing to advancements in health-monitoring technology.<\/jats:p>","DOI":"10.1371\/journal.pone.0325253","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:49:44Z","timestamp":1750168184000},"page":"e0325253","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["PIFR: A novel approach for analyzing pose angle-based human activity to automate fall detection in videos"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2222-4112","authenticated-orcid":true,"given":"Vungsovanreach","family":"Kong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5704-8820","authenticated-orcid":true,"given":"Saravit","family":"Soeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Munirot","family":"Thon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wan-Sup","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anand","family":"Nayyar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9962-1066","authenticated-orcid":true,"given":"Tae-Kyung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"pone.0325253.ref001","volume-title":"Fall response","author":"Agency for Healthcare Research and Quality","year":"2017"},{"key":"pone.0325253.ref002","doi-asserted-by":"crossref","first-page":"6384","DOI":"10.1109\/IEMBS.2006.260829","article-title":"Monocular 3D head tracking to detect falls of elderly people","volume":"2006","author":"C Rougier","year":"2006","journal-title":"Conf Proc IEEE Eng Med Biol Soc"},{"key":"pone.0325253.ref003","volume-title":"Falls","author":"World Health Organization","year":"2021"},{"key":"pone.0325253.ref004","doi-asserted-by":"crossref","DOI":"10.18356\/919c4178-en","volume-title":"World Population Ageing 2020 Highlights","author":"United Nations","year":"2020"},{"key":"pone.0325253.ref005","article-title":"Falls in older persons: risk factors and prevention","volume-title":"The Second Fifty Years: Promoting Health and Preventing Disability","author":"RL Berg","year":"1992"},{"issue":"1","key":"pone.0325253.ref006","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1186\/s13018-022-03222-1","article-title":"Global prevalence of falls in the older adults: a comprehensive systematic review and meta-analysis","volume":"17","author":"N Salari","year":"2022","journal-title":"J Orthop Surg Res"},{"key":"pone.0325253.ref007","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1186\/s12916-015-0390-8","article-title":"Prevalence, risk factors and disability associated with fall-related injury in older adults in low- and middle-incomecountries: results from the WHO Study on global AGEing and adult health (SAGE)","volume":"13","author":"J Stewart Williams","year":"2015","journal-title":"BMC Med"},{"issue":"21","key":"pone.0325253.ref008","doi-asserted-by":"crossref","first-page":"21999","DOI":"10.1109\/JIOT.2022.3181701","article-title":"Development of a real-time wearable fall detection system in the context of internet of things","volume":"9","author":"Z Qian","year":"2022","journal-title":"IEEE Internet Things J"},{"issue":"3","key":"pone.0325253.ref009","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1109\/TETC.2020.3027454","article-title":"Online fall detection using recurrent neural networks on smart wearable devices","volume":"9","author":"M Musci","year":"2021","journal-title":"IEEE Trans Emerg Topics Comput"},{"issue":"1","key":"pone.0325253.ref010","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/s12652-019-01214-4","article-title":"Fall detection and human activity classification using wearable sensors and compressed sensing","volume":"11","author":"O Kerdjidj","year":"2019","journal-title":"J Ambient Intell Human Comput"},{"key":"pone.0325253.ref011","doi-asserted-by":"crossref","unstructured":"Mehta V, Dhall A, Pal S, Khan SS. Motion and region aware adversarial learning for fall detection with thermal imaging. In: 2020 25th International Conference on Pattern Recognition (ICPR), 2021. pp. 6321\u20136328. doi: 10.1109\/icpr48806.2021.9412632","DOI":"10.1109\/ICPR48806.2021.9412632"},{"key":"pone.0325253.ref012","doi-asserted-by":"crossref","unstructured":"Ogawa Y, Naito K. Fall detection scheme based on temperature distribution with IR array sensor. In: 2020 IEEE International Conference on Consumer Electronics (ICCE), 2020. doi: 10.1109\/icce46568.2020.9043000","DOI":"10.1109\/ICCE46568.2020.9043000"},{"issue":"1","key":"pone.0325253.ref013","doi-asserted-by":"crossref","first-page":"130","DOI":"10.3390\/mi14010130","article-title":"A non-contact fall detection method for bathroom application based on MEMS infrared sensors","volume":"14","author":"C He","year":"2023","journal-title":"Micromachines (Basel)"},{"key":"pone.0325253.ref014","doi-asserted-by":"crossref","first-page":"33532","DOI":"10.1109\/ACCESS.2021.3061626","article-title":"Fall detection and activity recognition using human skeleton features","volume":"9","author":"H Ramirez","year":"2021","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0325253.ref015","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/s41666-019-00061-4","article-title":"DeepFall: non-invasive fall detection with deep spatio-temporal convolutional autoencoders","volume":"4","author":"J Nogas","year":"2019","journal-title":"J Healthc Inform Res"},{"key":"pone.0325253.ref016","doi-asserted-by":"crossref","unstructured":"Chen Y, Du R, Luo K, Xiao Y. Fall detection system based on real-time pose estimation and SVM. In: 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), 2021. doi: 10.1109\/icbaie52039.2021.9390068","DOI":"10.1109\/ICBAIE52039.2021.9390068"},{"key":"pone.0325253.ref017","doi-asserted-by":"crossref","first-page":"4136","DOI":"10.1109\/ACCESS.2024.3525183","article-title":"Automated defect detection in solar cell images using deep learning algorithms","volume":"13","author":"M Abdelsattar","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0325253.ref018","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317619","article-title":"Evaluating machine learning and deep learning models for predicting wind turbine power output from environmental factors","volume":"20","author":"M Abdelsattar","year":"2025","journal-title":"PLoS One"},{"key":"pone.0325253.ref019","doi-asserted-by":"crossref","first-page":"100969","DOI":"10.1016\/j.rineng.2023.100969","article-title":"Low-cost autonomous car level 2: design and implementation for conventional vehicles","volume":"17","author":"MS Mohammed","year":"2023","journal-title":"Results Eng"},{"key":"pone.0325253.ref020","doi-asserted-by":"crossref","unstructured":"Faisal MM, Mohammed MS, Abduljabar AM, Abdulhussain SH, Mahmmod BM, Khan W, et al. Object detection and distance measurement using AI. In: 2021 14th International Conference on Developments in eSystems Engineering (DeSE), 2021. 559\u201365. doi: 10.1109\/dese54285.2021.9719469","DOI":"10.1109\/DeSE54285.2021.9719469"},{"issue":"1","key":"pone.0325253.ref021","doi-asserted-by":"crossref","first-page":"329","DOI":"10.3390\/app11010329","article-title":"A framework for fall detection based on OpenPose skeleton and LSTM\/GRU models","volume":"11","author":"C-B Lin","year":"2020","journal-title":"Appl Sci"},{"issue":"5","key":"pone.0325253.ref022","doi-asserted-by":"crossref","first-page":"744","DOI":"10.3390\/sym12050744","article-title":"Fall detection based on key points of human-skeleton using OpenPose","volume":"12","author":"W Chen","year":"2020","journal-title":"Symmetry"},{"issue":"23","key":"pone.0325253.ref023","doi-asserted-by":"crossref","first-page":"6966","DOI":"10.3390\/s20236966","article-title":"A two-stage fall recognition algorithm based on human posture features","volume":"20","author":"K Han","year":"2020","journal-title":"Sensors (Basel)"},{"key":"pone.0325253.ref024","doi-asserted-by":"crossref","unstructured":"Dang TN, Kim Le T, Hong TP, Nguyen VB. Fast and accurate fall detection and warning system using image processing technology. In: 2021 International Conference on Advanced Technologies for Communications (ATC), 2021. 207\u201310. doi: 10.1109\/atc52653.2021.9598204","DOI":"10.1109\/ATC52653.2021.9598204"},{"key":"pone.0325253.ref025","doi-asserted-by":"crossref","unstructured":"Bugarin CAQ, Lopez JMM, Pineda SGM, Sambrano MaFC, Loresco PJM. Machine vision-based fall detection system using MediaPipe pose with IoT monitoring and alarm. In: 2022 IEEE 10th Region 10 Humanitarian Technology Conference (R10-HTC), 2022. doi: 10.1109\/r10-htc54060.2022.9929527","DOI":"10.1109\/R10-HTC54060.2022.9929527"},{"issue":"11","key":"pone.0325253.ref026","doi-asserted-by":"crossref","first-page":"3991","DOI":"10.3390\/s22113991","article-title":"Human activity recognition by sequences of skeleton features","volume":"22","author":"H Ramirez","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0325253.ref027","doi-asserted-by":"crossref","first-page":"91273","DOI":"10.1109\/ACCESS.2022.3202293","article-title":"Elderly fall detection based on improved YOLOv5s network","volume":"10","author":"T Chen","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0325253.ref028","doi-asserted-by":"crossref","first-page":"94249","DOI":"10.1109\/ACCESS.2022.3203174","article-title":"Exploring human pose estimation and the usage of synthetic data for elderly fall detection in real-world surveillance","volume":"10","author":"S Juraev","year":"2022","journal-title":"IEEE Access"},{"issue":"15","key":"pone.0325253.ref029","doi-asserted-by":"crossref","first-page":"5482","DOI":"10.3390\/s22155482","article-title":"A lightweight subgraph-based deep learning approach for fall recognition","volume":"22","author":"Z Zhao","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"12","key":"pone.0325253.ref030","doi-asserted-by":"crossref","first-page":"4544","DOI":"10.3390\/s22124544","article-title":"Using deep neural networks for human fall detection based on pose estimation","volume":"22","author":"M Salimi","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"12","key":"pone.0325253.ref031","doi-asserted-by":"crossref","first-page":"6916","DOI":"10.3390\/app13126916","article-title":"A Robust and automated vision-based human fall detection system using 3D multi-stream CNNs with an image fusion technique","volume":"13","author":"T Alanazi","year":"2023","journal-title":"Appl Sci"},{"key":"pone.0325253.ref032","doi-asserted-by":"crossref","unstructured":"Soontornnapar T, Ploysuwan T. Fall detection approach using variational autoencoders with self-attention features. In: J Telecommun Inf Technol (ECTI-CON) 20th International Conference on Electrical Engineering\/Electronics, Computer. IEEE; 2023, 2023. 1\u20134.","DOI":"10.1109\/ECTI-CON58255.2023.10153189"},{"key":"pone.0325253.ref033","doi-asserted-by":"crossref","unstructured":"Miawarni H, Sardjono TA, Setijadi E, Wijayanti, Purnomo MH. Fall Detection System for Elderly (FDS-E) using Low-cost Camera Based on LSTM and OpenPose. In: 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2023. 1\u20136. doi: 10.1109\/i2mtc53148.2023.10175919","DOI":"10.1109\/I2MTC53148.2023.10175919"},{"key":"pone.0325253.ref034","doi-asserted-by":"crossref","unstructured":"Hegde A, Patil O, Belurgikar S, Jani PV. A novel approach to fall detection system using computer vision. In: 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS), 2023. 1906\u201313. doi: 10.1109\/icaccs57279.2023.10113049","DOI":"10.1109\/ICACCS57279.2023.10113049"},{"key":"pone.0325253.ref035","doi-asserted-by":"crossref","unstructured":"Chan XE, Goh CP. Computer vision-based home accident detection and response system for elderly care. In: 2024 3rd International Conference on Digital Transformation and Applications (ICDXA), 2024. 147\u201351. doi: 10.1109\/icdxa61007.2024.10470602","DOI":"10.1109\/ICDXA61007.2024.10470602"},{"issue":"11","key":"pone.0325253.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3687125","article-title":"Learning and Vision-based approach for Human fall detection and classification in naturally occurring scenes using video data","volume":"23","author":"S Singh","year":"2024","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"pone.0325253.ref037","doi-asserted-by":"crossref","unstructured":"Liu X, Yow K-C. Human fall detection based on ResNet and LSTM network in surveillance cameras. In: 2024 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), 2024. 1\u20136. doi: 10.1109\/pacrim61180.2024.10690207","DOI":"10.1109\/PACRIM61180.2024.10690207"},{"key":"pone.0325253.ref038","doi-asserted-by":"crossref","unstructured":"Kandukuru TK, Thangavel SK, Jeyakumar G. Computer vision based algorithms for detecting and classification of activities for fall recognition on real time video. In: 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT), 2024. 1\u20136. doi: 10.1109\/aiiot58432.2024.10574542","DOI":"10.1109\/AIIoT58432.2024.10574542"},{"key":"pone.0325253.ref039","volume-title":"Computer-aided fall recognition using a three-stream spatial-temporal GCN model with adaptive feature aggregation","author":"J Shin","year":"2024"},{"key":"pone.0325253.ref040","doi-asserted-by":"crossref","unstructured":"Reis M, Rojas YEL, Gatto BB, Colonna JG. Detection of elderly falls. In: Video. Streams using skeleton key points and transformer networks. 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2024. 1\u20136.","DOI":"10.1109\/SIBGRAPI62404.2024.10716330"},{"issue":"1","key":"pone.0325253.ref041","doi-asserted-by":"crossref","first-page":"453","DOI":"10.3390\/app15010453","article-title":"FD-YOLO: a YOLO network optimized for fall detection","volume":"15","author":"H Hwang","year":"2025","journal-title":"Appl Sci"},{"key":"pone.0325253.ref042","first-page":"360","article-title":"RSTAN: residual spatio-temporal attention network for end-to-end human fall detection","volume-title":"Lecture Notes in Computer Science","author":"Y Jiang","year":"2024"},{"issue":"3","key":"pone.0325253.ref043","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.cmpb.2014.09.005","article-title":"Human fall detection on embedded platform using depth maps and wireless accelerometer","volume":"117","author":"B Kwolek","year":"2014","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0325253.ref044","volume-title":"Multiple cameras fall dataset","author":"E Auvinet","year":"2010"},{"key":"pone.0325253.ref045","unstructured":"Jocher G, Qiu J, Chaurasia A. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics. 2023."},{"issue":"3","key":"pone.0325253.ref046","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"pone.0325253.ref047","author":"DMW Powers","year":"2020","journal-title":"Evaluation: From precision, recall and f-measure to roc, informedness, markedness & correlation"},{"key":"pone.0325253.ref048","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1007\/978-3-030-63416-2_660","article-title":"Object detection","volume-title":"Computer Vision","author":"Y Amit","year":"2021"},{"key":"pone.0325253.ref049","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511975837","volume-title":"Fundamentals of Object Tracking","author":"S Challa","year":"2011"},{"key":"pone.0325253.ref050","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1007\/978-3-030-63416-2_584","article-title":"Human pose estimation","volume-title":"Computer vision: A reference guide","author":"L Sigal","year":"2021"},{"key":"pone.0325253.ref051","unstructured":"Asif U, Mashford B, Von Cavallar S, Yohanandan S, Roy S, Tang J. Privacy-preserving human fall detection using video data. In: Machine Learning for Health Workshop, 2020. 39\u201351."},{"issue":"1","key":"pone.0325253.ref052","article-title":"Fall detection and direction judgment based on posture estimation","volume":"2022","author":"C Yuan","year":"2022","journal-title":"Discr Dynam Nat Soc"},{"key":"pone.0325253.ref053","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.patrec.2018.08.031","article-title":"Spatio-temporal fall event detection in complex scenes using attention guided LSTM","volume":"130","author":"Q Feng","year":"2020","journal-title":"Patt Recogn Lett"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:50:01Z","timestamp":1750168201000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325253"}},"subtitle":[],"editor":[{"given":"Alessandro","family":"Bruno","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":53,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0325253","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]}}}