Número

Vol. 12 Núm. 2 (2024): Julio - Diciembre

Derechos de autor 2024 Investigación e Innovación en Ingenierías

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.

La revista Investigación e Innovación en Ingenierías respeta los derechos morales de cada autor, sin embargo los autores ceden los derechos patrimoniales de sus artículos, y al mismo tiempo certifican a través de una carta que su trabajo es inédito y no ha sido publicado anteriormente.

Comparative Study Of Computer Vision Algorithms For Fall Detection

https://doi.org/10.17081/invinno.12.2.6929
José Camilo Eraso Guerrero
Universidad CESMAG
https://orcid.org/0000-0002-2264-6385
Elena Muñoz España
Universidad del Cauca
https://orcid.org/0000-0002-3919-563X
Mariela Muñoz Añasco
Universidad del Cauca
https://orcid.org/0000-0003-4392-947X
Miller Manuel Rúales Luna
Universidad CESMAG
https://orcid.org/0009-0001-2496-7959

Corresponding Author(s) : José Camilo Eraso Guerrero

jceraso@unicesmag.edu.co

Investigación e Innovación en Ingenierías, Vol. 12 Núm. 2 (2024): Julio - Diciembre

Resumen

Objetivo: Comparar el rendimiento de tres algoritmos de reconocimiento de caídas humanas, centrados en visión computacional. La comparación se llevará a cabo evaluando su desempeño en diversas bases de datos comúnmente utilizadas por la comunidad científica, así como en una nueva base de datos denominada CAUCAFall. Metodología: En el estudio se comparan tres algoritmos, seleccionados mediante una revisión sistemática que consideró artículos que trabajan con visión artificial, cámaras RGB y bases de datos públicas. Los algoritmos seleccionados se centran en extracción de características y redes neuronales convolucionales usando YOLO Y OPENPOSE. Resultados: El estudio encontró que los tres algoritmos tienen buen rendimiento en bases de datos comúnmente utilizadas por la comunidad científica. Sin embargo, se observó un desempeño inferior al evaluar los algoritmos en CAUCAFall, que contiene entornos poco controlados y más cercano a la realidad.  Conclusiones: La investigación destaca la importancia de evaluar algoritmos de reconocimiento de caídas humanas en escenarios más realistas. Se plantea la importancia de futuras investigaciones que se centren en crear y evaluar algoritmos en bases de datos que contengan escenarios más cercanos a la realidad, lo que sería un avance significativo en el área de reconocimiento de caídas humanas.

[1]
J. C. Eraso Guerrero, E. Muñoz España, M. Muñoz Añasco, y M. M. Rúales Luna, «Comparative Study Of Computer Vision Algorithms For Fall Detection», Investigación e Innovación en Ingenierías, vol. 12, n.º 2, pp. 38–57, ago. 2024.
Descargar cita
Endnote/Zotero/Mendeley (RIS)
BibTeX
Referencias
  • OMS | “Datos interesantes acerca del envejecimiento,” WHO. (2015). En: https://www.who.int/ageing/about/facts/es/
  • G. Horng y K. Chen, “The Smart Fall Detection Mechanism for Healthcare Under Free‑Living Conditions,” Springer, Wireless Personal Communications. 118:715–753, 2021. https://doi.org/10.1007/s11277-020-08040-4.
  • N. Thakur y C. Han, “A Study of Fall Detection in Assisted Living: Identifying and Improving the Optimal Machine Learning Method,” J. Sens. Actuator Netw. 10, 39, 2021. https://doi.org/10.3390/jsan10030039
  • F. Shu y J. Shu, “An eight‑camera fall detection system using human fall pattern recognition via machine Learning by a low‑cost android box,” Scientific Reports, 2021. 11:2471. https://doi.org/10.1038/s41598-021-81115-9
  • H. Li, H. Shrestha, F. Fioranelli, K. Le y H. Heidari, “Hierarchical Classification on Multimodal Sensing for Human Activity Recogintion and Fall Detection,” 2018 IEEE SENSORS, pp. 1–4. 2018. Doi: 10.1109/ICSENS.2018.8589797
  • S. Amiri, M. Pourazad, P. Nasiopoulos y V. Leung, “Improved human action recognition in a smart home environment setting,” IRBM. Vol. (35), no. 6, pp. 321–328, 2014.
  • M. Yu, Y. Yu, Y. Rhuma, S. Naqvi, L. Wang y J. Chambers, “An online one class support vector machine-based person-specific fall detection system for monitoring an elderly individual in a room environment,” IEEE J. Biomed. Heal. Informatics. Vol. (17), no. 6, pp. 1002–1014, 2013.
  • F. Concone, G. Re y M. Morana, “A Fog-Based Application for Human Activity Recognition Using Personal Smart Devices,” ACM Transactions on Internet Technology. Vol. (19), no. 2, 2019.
  • G. Debard, M. Mertens, M. Deschodt, E. Vlaeyen, E. Devriendt, E. Dejaeger, K. Milisen, J. Tournoy, T. Croonenborghs, T. Goedemé, T. Tuytelaars, B. Vanrumste," Camera-based fall detection using real-world versus simulated data: how far are we from the solution?," Journal of Ambient Intelligence and Smart Environments, pp. 1-19, 2015.
  • Y. Fan, M. Levine, G. Wen, S. Qiu," A deep neural network for real-time detection of falling humans in naturally occurring scenes," Neurocomputing. Vol.260, pp.43-18, oct, 2017.
  • S. Nwe Htun, T. Zin y P. Tin. " Image Processing Technique and Hidden Markov Model for an Elderly Care Monitoring System," J. Imaging 6, 49, 2020. doi:10.3390/jimaging6060049
  • Q. Feng, C.Gao, L. Wang, Y. Zhao, T. Song, Q. Li, “Spatio-temporal fall event detection in complex scenes using attention guided LSTM”, Pattern Recognition Letters .2020. doi: https://doi.org/10.1016/j.patrec.2018.08.031
  • Q. Xu, G. Huang, M. Yu, Y. Guo" Fall prediction based on key points of human bones," Physica A. 2019. https://doi.org/10.1016/j.physa.2019.123205
  • J.C. Eraso, E. Muñoz, M. Muñoz, J. Pinto, “Dataset for human fall recognition in an uncontrolled environment,” Data in Brief, Volume 45, December 2022. https://doi.org/10.1016/j.dib.2022.108610
  • G. Goudelis, G. Tsatiris, T. Karpouzis y S. Kollias, “Fall detection using history triple features,” 8th ACM Int. Conf. PErvasive Technol. Relat. to Assist. Environ. PETRA 2015 - Proc., 2015.
  • Z. Khan y W. Sohn, “Abnormal human activity recognition system based on R-transform and kernel discriminant technique for elderly home care,” IEEE Trans. Consum. Electron. Vol. (57), no. 4, pp. 2021.
  • M. Yu, S. Naqvi, A. Rhuma y J. Chambers, “One class boundary method classifiers for application in a video-based fall detection system,” IET Comput. Vis. Vol. (6), no. 2, pp. 90–100, 2012.
  • H. Foroughi, B. Aski, y H. Pourreza, “Intelligent Video Surveillance for Monitoring Fall Detection of Elderly in Home Environment,” Proc. 11th Int. Conf. Comput. Inf. Technol. pp. 219–224, 2008.
  • C. Rougier, J. Meunier, A. St-Arnaud y J. Rousseau, “Fall detection from human shape and motion history using video surveillance,” Proc. - 21st Int. Conf. Adv. Inf. Netw. Appl. Work. AINAW’07, 2007.
  • E. Auvinet, F. Multon, A. St-Arnaud, J. Rousseau y J. Meunier, “Fall detection with multiple cameras: An occlusion-resistant method based on 3-D silhouette vertical distribution,” IEEE Trans. Inf. Technol. Biomed. Vol. (15), no. 2, pp. 290–300, 2011.
  • A. Efros, A. Berg, G. Mori y J. Malik, “Recognizing action at a distance,” Proc. IEEE Int. Conf. Comput. Vis., pp. 726–733, 2008.
  • S. Zhang, Z. Wei, J. Nie, L. Huang, L. Wang y Z. Li, “A Review on Human Activity Recognition Using Vision-Based Method,” Journal of Healthcare Engineering, jul, 2017.
  • S. Venkatesha y M. Turk, “Human activity recognition using local shape descriptors,” Proc. - Int. Conf. Pattern Recognit., pp. 3704–3707, 2010.
  • X. Peng, L. Wang, X. Wang y Y. Qiao, “Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice,” Comput. Vis. Image Underst., 2016.
  • D.Dawn y S. Shaikh, “A comprehensive survey of human action recognition with spatio-temporal interest point (STIP) detector,” Vis. Comput., mar, 2015.
  • Y. Zhu, X. Zhao, Y. Fu y Y. Liu, Y, “Sparse coding on local spatial-temporal volumes for human action recognition,” Springer-Verlag Berlin Heidelberg, pp. 660–671, 2011.
  • Zhang et al., “A comprehensive survey of vision-based human action recognition methods,” Sensors (Switzerland). Vol. (19), no. 5, pp. 1–20, 2019.
  • Y. Hsieh y Y. Jeng, “Development of Home Intelligent Fall Detection IoT System based on Feedback Optical Flow Convolutional Neural Network,” IEEE Access. Vol. (6), pp. 6048 - 6057, 2017.
  • A.Núñez, G. Azkune, I. Arganda, " Vision-Based Fall Detection with Convolutional Neural Networks," Wireless Communications and Mobile Computing. 2017.
  • R. Espinosa, H. Ponceb, S. Gutiérreza, L. Martínez, J. Brievab, E. Moya, "A Vision-Based Approach for Fall Detection Using Multiple Cameras and Convolutional Neural Networks: A Case Study Using the UP-Fall Detection Dataset," Computers in Biology and Medicine. 2019. doi: https://doi.org/10.1016/j.compbiomed.2019.103520
  • M. Rahnemoonfar, H. Alkittawi, "Spatio-temporal convolutional neural network for elderly fall detection in depth video camerasl," IEEE International Conference on Big Data, 2018.
  • K. Adhikari, H. Bouchachia y H. Nait, "Activity Recognition for Indoor Fall Detection Using Convolutional Neural Network," International Conference on Machine Vision Applications (MVA). 2017.
  • N. Lu, X. Ren, J. Song, Y. Wu, "Visual Guided Deep Learning Scheme for Fall Detection, "IEEE Conference on Automation Science and Engineering (CASE). 2017.
  • Y. Guo, A. Shimada, H. Uchiyama, C. Ma, H. Nagahara, R. Taniguchi, " CNN for face detection with thermal image," 2018(16・18-23):2018.3.26 p.5-8, 2018. http://id.ndl.go.jp/bib/028999107
  • C. Khraief, F. Benzarti y H. Amiri, " Elderly fall detection based on multi-stream deep convolutional networks," Multimedia Tools and Applications volume 79, pages19537–19560, 2020. https://link.springer.com/article/10.1007%2Fs11042-020-08812-x
  • A. Kaid, K. Baina, J. Baina, "Reduce False Positive Alerts for Elderly Person Fall Video-Detection Algorithm by convolutional neural network model," Procedia Computer Science. Vol. 149, pp.2-11, 2019.
  • J. C. Eraso Guerrero, E. Muñoz España, y M. Muñoz Añasco, “Human Activity Recognition via Feature Extraction and Artificial Intelligence Techniques: A Review,” Tecnura, vol. 26, n.º 74, pp. 213–236, oct. 2022. https://doi.org/10.14483/22487638.17413
  • J. Gutiérrez, V. Rodríguez y S. Martin, “Comprehensive Review of Vision-Based Fall Detection Systems," Sensors 2021, 21, 947. 2021. https://doi.org/10.3390/s21030947
  • M. Kepski, B. Kwolek, “Embedded system for fall detection using body-worn accelerometer and depth sensor,” In Proceedings of the 2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Warsaw, Poland, 24–26 September 2015; Volume 2, pp. 755–759, 2015.
  • E. Auvinet, C. Rougier, J. Meunier, A. St-Arnaud, J. Rousseau, “Multiple Cameras Fall Data Set,” Technical Report Number 1350; University of Montreal: Montreal, QC, Canada, 8 July, 2011.
  • I. Charfi, J. Miteran, J. Dubois, M. Atri, R. Tourki, “Optimized spatio-temporal descriptors for real-time fall detection: Comparison of support vector machine and Adaboost-based classification,” J. Electron. Imaging 2013, 22, 041106,2013.
  • K. Adhikari, H. Bouchachia, H. Nait-Charif, “Activity recognition for indoor fall detection using convolutional neural network,” In Proceedings of the 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), Nagoya, Japan, 8–12 May, 2017.
  • L. Martínez-Villaseñor, H. Ponce, J. Brieva, E. Moya-Albor, J. Núñez-Martínez, C. Peñafort-Asturiano, “UP-Fall Detection Dataset: A Multimodal Approach”, Sensors 19(9), 1988: 2019. doi:10.3390/s19091988.
  • MOT Dataset. Available online: https://motchallenge.net/ (accessed on 11 November 2023).
  • T. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, C. Zitnick, “Microsoft coco: Common objects in context,” In Computer Vision-ECCV 2014, ECCV 2014. Lecture Notes in Computer Science; Springer: Cham, Swizerland, 2014; pp. 740–755
  • CENTRE FOR DIGITAL HOME—MMU. Available online: http://foe.mmu.edu.my/digitalhome/FallVideo.zip (accessed on 11 November 2023)
  • A. Shahroudy, J. Liu, T. Ng, G. Wang, “NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis,” In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 1010–1019, 2016.
  • F. Harrou, N. Zerrouki, Y. Sun, A. Houacine, “Vision-based fall detection system for improving safety of elderly people,” IEEE Instrum. Meas. Mag. 2017, 20, 49–55, 2017. [CrossRef]
  • S. Ali, R. Khan, A. Mahmood, M. Hassan, M. Jeon, “Using Temporal Covariance of Motion and Geometric Features via Boosting for Human Fall Detection,” Sensors 2018, 18, 1918, 2018. [CrossRef]
  • D. Kumar, A. Ravikumar, V. Dharmalingam, V. Kafle, “Elderly Health Monitoring System with Fall Detection Using Multi-Feature Based Person Tracking,” In Proceedings of the 2019 ITU Kaleidoscope: ICT for Health: Networks, Standards and Innovation (ITU K), Atlanta, GA, USA, 4–6 December 2019. [CrossRef]
  • F. Harrou, N. Zerrouki, Y. Sun, A. Houacine, “An Integrated Vision-Based Approach for Efficient Human Fall Detection in a Home Environment,” IEEE Access 2019, 7, 114966–114974, 2019. [CrossRef]
  • Y. Fan, M.D. Levine, G. Wen, S. Qiu, “ A deep neural network for real-time detection of falling humans in naturally occurring scenes,” Neurocomputing 2017, 260, 43–58.2017. [CrossRef]
  • W. Min, H. Cui, H. Rao, Z. Li, L. Yao, “Detection of Human Falls on Furniture Using Scene Analysis Based on Deep Learning and Activity Characteristics,” IEEE Access 2018, 6, 9324–9335. 2018. [CrossRef]
  • C. Ma, A. Shimada, H. Uchiyama, H. Nagahara, R. Taniguchi, “Fall detection using optical level anonymous image sensing system,” Opt. Laser Technol. 2019, 110, 44–61. 2019. [CrossRef]
  • R. Espinosa, H. Ponce, S. Gutiérrez, L. Martínez-Villaseñor, J. Brieva, E. Moya-Albor, “vision-based approach for fall detection using multiple cameras and convolutional neural networks: A case study using the UP-Fall detection Dataset,” Comput. Biol. Med. 2019, 115, 103520. 2019. [CrossRef]
  • B. Wang, J. Yu, K. Wang, X. Bao, K. Mao, “Fall Detection Based on Dual-Channel Feature Integration,“ IEEE Access 2020, 8, 103443–103453. 2020. [CrossRef]
  • S. Htun, T. Zin y H. Hama, “Virtual Grounding Point Concept for Detecting Abnormal and Normal Events in Home Care Monitoring Systems,” Appl. Sci. 2020, 10, 3005; 2020. doi:10.3390/app10093005
  • J. Redmon, A. Farhadi, “YOLOv3: An Incremental Improvement,”. 8 Apr, 2018 https://arxiv.org/abs/1804.02767
  • E. De la Hoz Domínguez, T. Fontalvo Herrera., y A. Mendoza Mendoza, “Machine Learning and SMEs: Opportunities for an improved decision -making process”, Investigación e Innovación en Ingenierías, vol. 8, n°. 1, 2020. DOI: https://doi.org/10.17081/invinno.8.1.3506
  • Z. Cao, G. Hidalgo, T. Simon, S. Wei y Y. A. Sheikh, “OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields,“ IEEE Transactions on Pattern Analysis and Machine Intelligence. 2019. https://github.com/CMU-Perceptual-Computing-Lab/openpose
Read More
Las biografías de los autores no están disponibles.
Descargar este archivo PDF
PDF