Abstract
Lower child mortality rates, advances in medicine, and cultural changes have increased life expectancy to above 60-years old in developed countries. Some countries expect that, by 2030, 20% of their population will be over 65 years old. The quality of life at this advanced age is highly dictated by the individual’s health, which will determine whether the elderly can engage in important activities to their well-being, independence, and personal satisfaction. Old age is accompanied by health problems caused by biological limitations and muscle weakness. This weakening facilitates the occurrence of falls, which are responsible for the deaths of approximately 646,000 people worldwide and, even when a minor fall occurs, it can still cause fractures, break bones, or damage soft tissues, which will not heal completely. Injuries and damages of this nature, in turn, will consume the self-confidence of the individual, diminishing their independence. In this work, we propose a method capable of detecting human falls in video sequences using multi-channel convolutional neural networks (CNN). Our method makes use of a 3D CNN fed with features previously extracted from each frame to generate a vector for each channels. Then, the vectors are concatenated, and a support vector machine (SVM) is applied to classify the vectors and indicate whether or not there was a fall. We experiment with four types of features, namely: (i) optical flow, (ii) visual rhythm, (iii) pose estimation, and (iv) saliency map. The benchmarks used (UR Fall Detection Dataset (URFD) [33] and (ii) Fall Detection Dataset (FDD) [12]) are publicly available and our results are compared to those in the literature. The metrics selected for evaluation are balanced accuracy, accuracy, sensitivity, and specificity. Our results are competitive with those obtained by the state of the art on both URFD and FDD datasets. To the authors’ knowledge, we are the first to perform cross-tests between the datasets in question and to report results for the balanced accuracy metric. The proposed method is able to detect falls in the selected benchmarks. Fall detection, as well as activity classification in videos, is strongly related to the network’s ability to interpret temporal information and, as expected, optical flow is the most relevant feature for detecting falls.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org
A. Abobakr, M. Hossny, S. Nahavandi, A skeleton-free fall detection system from depth images using random decision forest. IEEE Syst. J. 12(3), 2994–3005 (2017)
D.T. Anderson, J.M. Keller, M. Skubic, X. Chen, Z. He, Recognizing falls from silhouettes, in International Conference of the IEEE Engineering in Medicine and Biology Society (2006), pp. 6388–6391
L. Anishchenko, Machine learning in video surveillance for fall detection, in Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (IEEE, 2018), pp. 99–102
S. Bhandari, N. Babar, P. Gupta, N. Shah, S. Pujari, A novel approach for fall detection in home environment, in IEEE 6th Global Conference on Consumer Electronics (IEEE, 2017), pp. 1–5
G. Bradski, The openCV library. Dobb’s J. Softw. Tools 120, 122–125 (2000)
Z. Cao, T. Simon, S.E. Wei, Y. Sheikh, Realtime multi-person 2D pose estimation using part affinity fields, in IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 7291–7299
S. Carneiro, G. Silva, G. Leite, R. Moreno, S. Guimaraes, H. Pedrini, Deep convolutional multi-stream network detection system applied to fall identification in video sequences, in 15th International Conference on Machine Learning and Data Mining (2019a), pp. 681–695
S. Carneiro, G. Silva, G. Leite, R. Moreno, S. Guimaraes, H. Pedrini, Multi-stream deep convolutional network using high-level features applied to fall detection in video sequences, in 26th International Conference on Systems, Signals and Image Processing (2019b), pp. 293–298
J. Carreira, A. Zisserman, Quo vadis, action recognition? a new model and the kinetics dataset, in Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6299–6308
I. Charfi, J. Miteran, J. Dubois, M. Atri, R. Tourki, Definition and performance evaluation of a robust svm based fall detection solution, in International Conference on Signal Image Technology and Internet Based Systems, vol. 12 (2012), pp. 218–224
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 22(4), 041106 (2013)
F. Chollet, Keras (2015). https://keras.io
J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, L. Fei-Fei, Imagenet: a large–scale hierarchical image database, in IEEE Conference on Computer Vision and Pattern Recognition (2009), pp. 248–255
L. Deng, D. Yu, Deep learning: methods and applications. Found. Trends Signal Process. 7(3–4), 197–387 (2014)
A. Edgcomb, F. Vahid, Automated fall detection on privacy-enhanced video, in Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2012), pp. 252–255
K. Fan, P. Wang, S. Zhuang, Human fall detection using slow feature analysis. Multimed. Tools Appl. 78(7), 9101–9128 (2018a)
Y. Fan, G. Wen, D. Li, S. Qiu, M.D. Levine, Early event detection based on dynamic images of surveillance videos. J. Vis. Commun. Image Represent. 51, 70–75 (2018b)
G. Farnebäck, Two–frame motion estimation based on polynomial expansion, in Scandinavian Conference on Image Analysis (2003), pp. 363–370
S. Gasparrini, E. Cippitelli, E. Gambi, S. Spinsante, J. Wåhslén, I. Orhan, T. Lindh, Proposal and experimental evaluation of fall detection solution based on wearable and depth data fusion, in International Conference on ICT Innovations (Springer, 2015), pp. 99–108
M.A. Goodale, A.D. Milner, Separate visual pathways for perception and action. Trends Neurosci. 15(1), 20–25 (1992)
I. Goodfellow, Y. Bengio, A. Courville, Y. Bengio, Deep Learning (MIT Press, 2016)
F. Harrou, N. Zerrouki, Y. Sun, A. Houacine, Vision-based fall detection system for improving safety of elderly people. IEEE Instrum. & Meas. Mag. 20(6), 49–55 (2017)
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778
D.L. Heymann, T. Prentice, L.T. Reinders, The World Health Report: a Safer Future: global Public Health Security in the 21st Century (World Health Organization, 2007)
Z. Huang, Y. Liu, Y. Fang, B.K. Horn, Video-based fall detection for seniors with human pose estimation, in 4th International Conference on Universal Village (IEEE, 2018), pp. 1–4
E. Jones, T. Oliphant, P. Peterson, SciPy: open source scientific tools for python (2001). http://www.scipy.org
O.O. Khin, Q.M. Ta, C.C. Cheah, Development of a wireless sensor network for human fall detection, in International Conference on Real-Time Computing and Robotics (IEEE, 2017), pp. 273–278
Y. Kong, J. Huang, S. Huang, Z. Wei, S. Wang, Learning spatiotemporal representations for human fall detection in surveillance video. J. Vis. Commun. Image Represent. 59, 215–230 (2019)
A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012)
T. Kukharenko, V. Romanenko, Picking a human fall detection algorithm for wrist–worn electronic device, in IEEE First Ukraine Conference on Electrical and Computer Engineering (2017), pp. 275–277
V.S. Kumar, K.G. Acharya, B. Sandeep, T. Jayavignesh, A. Chaturvedi, Wearable sensor–based human fall detection wireless system, in Wireless Communication Networks and Internet of Things (Springer, 2018), pp. 217–234
B. Kwolek, M. Kepski, Human fall detection on embedded platform using depth maps and wireless accelerometer. Comput. Methods Programs Biomed. 117(3), 489–501 (2014)
B. Kwolek, M. Kepski, Improving fall detection by the use of depth sensor and accelerometer. Neurocomputing 168, 637–645 (2015)
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
T. Lee, A. Mihailidis, An intelligent emergency response system: preliminary development and testing of automated fall Detection. J. Telemed. Telecare 11(4), 194–198 (2005)
G. Leite, G. Silva, H. Pedrini, Fall detection in video sequences based on a three-stream convolutional neural network, in 18th IEEE International Conference on Machine Learning and Applications (ICMLA) (Boca Raton-FL, USA, 2019), pp. 191–195
G. Leite, G. Silva, H. Pedrini, Fall detection (2020). https://github.com/Lupins/fall_detection
H. Li, K. Mueller, X. Chen, Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation. Comput. Res. Repos. (2017a)
X. Li, T. Pang, W. Liu, T. Wang, Fall detection for elderly person care using convolutional neural networks, in 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (2017b), pp. 1–6
W.N. Lie, A.T. Le, G.H. Lin, Human fall-down event detection based on 2D skeletons and deep learning approach, in International Workshop on Advanced Image Technology (2018), pp. 1–4
B.S. Lin, J.S. Su, H. Chen, C.Y. Jan, A fall detection system based on human body silhouette, in 9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IEEE, 2013), pp. 49–52
N. Lu, Y. Wu, L. Feng, J. Song, Deep learning for fall detection: 3D-CNN combined with LSTM on video kinematic data. IEEE J. Biomed. Health Inform. 23(1), 314–323 (2018)
B.D. Lucas, T. Kanade, An iterative image registration technique with an application to stereo vision, in International Joint Conference on Artificial Inteligence (1981), pp. 121–130
F. Luna-Perejon, J. Civit-Masot, I. Amaya-Rodriguez, L. Duran-Lopez, J.P. Dominguez-Morales, A. Civit-Balcells, A. Linares-Barranco, An automated fall detection system using recurrent neural networks, in Conference on Artificial Intelligence in Medicine in Europe (Springer, 2019), pp. 36–41
M.M. Lusardi, S. Fritz, A. Middleton, L. Allison, M. Wingood, E. Phillips, Determining risk of falls in community dwelling older adults: a systematic review and meta-analysis using posttest probability. J. Geriatr. Phys. Ther. 40(1), 1–36 (2017)
X. Ma, H. Wang, B. Xue, M. Zhou, B. Ji, Y. Li, Depth-based human fall detection via shape features and improved extreme learning machine. J. Biomed. Health Inform. 18(6), 1915–1922 (2014)
L. Meng, B. Zhao, B. Chang, G. Huang, W. Sun, F. Tung, L. Sigal, Interpretable Spatio-Temporal Attention for Video Action Recognition (2018), pp. 1–10. arXiv preprint arXiv:181004511
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 6, 9324–9335 (2018)
M.N.H. Mohd, Y. Nizam, S. Suhaila, M.M.A. Jamil, An optimized low computational algorithm for human fall detection from depth images based on support vector machine classification, in IEEE International Conference on Signal and Image Processing Applications (2017), pp. 407–412
T.P. Moreira, D. Menotti, H. Pedrini, First-person action recognition through visual rhythm texture description, in International Conference on Acoustics (Speech and Signal Processing, IEEE, 2017), pp. 2627–2631
E.B. Nievas, O.D. Suarez, G.B. García, R. Sukthankar, Violence detection in video using computer vision techniques, in International Conference on Computer Analysis of Images and Patterns (Springer, 2011), pp. 332–339
Y. Nizam, M.N.H. Mohd, M.M.A. Jamil, Human fall detection from depth images using position and velocity of subject. Procedia Comput. Sci. 105, 131–137 (2017)
A. Núñez-Marcos, G. Azkune, I. Arganda-Carreras, Vision-based fall detection with convolutional neural networks. Wirel. Commun. Mob. Comput. 2017, 1–16 (2017)
T.E. Oliphant, Guide to NumPy, 2nd edn. (CreateSpace Independent Publishing Platform, USA, USA, 2015)
L. Panahi, V. Ghods, Human fall detection using machine vision techniques on RGB-D images. Biomed. Signal Process. Control 44, 146–153 (2018)
P.S. Sase, S.H. Bhandari, Human fall detection using depth videos, in 5th International Conference on Signal Processing and Integrated Networks (IEEE, 2018), pp. 546–549
C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local SVM approach, in 17th International Conference on Pattern Recognition, vol. 3 (IEEE, 2004), pp 32–36
K. Sehairi, F. Chouireb, J. Meunier, Elderly fall detection system based on multiple shape features and motion analysis, in International Conference on Intelligent Systems and Computer Vision (IEEE, 2018), pp. 1–8
A. Shojaei-Hashemi, P. Nasiopoulos, J.J. Little, M.T. Pourazad, Video–based human fall detection in smart homes using deep learning, in IEEE International Symposium on Circuits and Systems (2018), pp. 1–5
K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27, 568–576 (2014a)
K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition (2014b), pp. 1–14. arXiv, arXiv:14091556
K. Simonyan, A. Vedaldi, A. Zisserman, Deep inside convolutional networks: visualising image classification models and saliency maps. Comput. Res. Repos. (2013)
D. Smilkov, N. Thorat, B. Kim, F. Viégas, M. Wattenberg, Smoothgrad: removing noise by adding noise (2017), pp. 1–10. arXiv preprint arXiv:170603825
M. Sundararajan, A. Taly, Q. Yan, Axiomatic attribution for deep networks, in 34th International Conference on Machine Learning, vol. 70, pp. 3319–3328 (JMLR.org, 2017)
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, going deeper with convolutions, in IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 1–9
S.K. Tasoulis, G.I. Mallis, S.V. Georgakopoulos, A.G. Vrahatis, V.P. Plagianakos, I.G. Maglogiannis, Deep learning and change detection for fall recognition, in Engineering Applications of Neural Networks, ed. by J. Macintyre, L. Iliadis, I. Maglogiannis, C. Jayne (Springer International Publishing, Cham, 2019), pp. 262–273
The Joint Commission, Fall reduction program—definition of a fall (2001)
B.S. Torres, H. Pedrini, Detection of complex video events through visual rhythm. Vis. Comput. 34(2), 145–165 (2018)
US Department of Veterans Affairs, Falls policy overview (2019). http://www.patientsafety.va.gov/docs/fallstoolkit14/05_falls_policy_overview_v5.docx
F.B. Valio, H. Pedrini, N.J. Leite, Fast rotation-invariant video caption detection based on visual rhythm. in Iberoamerican Congress on Pattern Recognition (Springer, 2011), pp. 157–164
M. Vallejo, C.V. Isaza, J.D. Lopez, Artificial neural networks as an alternative to traditional fall detection methods, in 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2013), pp. 1648–1651
G. Van Rossum, F.L. Jr Drake, Python reference manual. Tech. Rep. Report CS-R9525, Centrum voor Wiskunde en Informatica, Amsterdam (1995)
L. Wang, Y. Xiong, Z. Wang, Y. Qiao, Towards good practices for very deep two-stream convnets (2015), pp. 1–5. arXiv preprint arXiv:150702159
M. Wani, F. Bhat, S. Afzal, A. Khan, Advances in Deep Learning (Springer, 2020)
World Health Organization, Global Health and Aging (2011)
World Health Organization, Fact sheet falls (2012)
World Health Organization, World Report on Ageing and Health (2015)
T. Xu, Y. Zhou, J. Zhu, New advances and challenges of fall detection systems: a survey. Appl. Sci. 8(3), 418 (2018)
M. Yu, S.M. Naqvi, J. Chambers, A robust fall detection system for the elderly in a smart room, in IEEE International Conference on Acoustics Speech and Signal Processing (2010), pp. 1666–1669
N. Zerrouki, A. Houacine, Combined curvelets and hidden Markov models for human fall detection. Multimed. Tools Appl. 77(5), 6405–6424 (2018)
N. Zerrouki, F. Harrou, Y. Sun, A. Houacine, Vision-based human action classification using adaptive boosting algorithm. IEEE Sens. J. 18(12), 5115–5121 (2018)
Z. Zhang, V. Athitsos, Fall detection by zhong zhang and vassilis athitsos (2020). http://vlm1.uta.edu/~zhangzhong/fall_detection/
S. Zhao, W. Li, W. Niu, R. Gravina, G. Fortino, Recognition of human fall events based on single tri–axial gyroscope, in IEEE 15th International Conference on Networking, Sensing and Control (2018), pp. 1–6
F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, Q. He, A comprehensive survey on transfer learning (2019), pp. 1–27. arXiv preprint arXiv:191102685
Y. Zigel, D. Litvak, I. Gannot, A method for automatic fall detection of elderly people using floor vibrations and sound-proof of concept on human mimicking doll falls. IEEE Trans. Biomed. Eng. 56(12), 2858–2867 (2009)
Z. Zuo, B. Wei, F. Chao, Y. Qu, Y. Peng, L. Yang, Enhanced gradient-based local feature descriptors by saliency map for egocentric action recognition. Appl. Syst. Innov. 2(1), 1–14 (2019)
Acknowledgements
The authors are thankful to FAPESP (grant #2017/12646-3), CNPq (grant #309330/2018-7), and CAPES for their financial support, as well as Semantix Brasil for the infrastructure and support provided during the development of the present work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Leite, G.V., da Silva, G.P., Pedrini, H. (2021). Three-Stream Convolutional Neural Network for Human Fall Detection. In: Wani, M.A., Khoshgoftaar, T.M., Palade, V. (eds) Deep Learning Applications, Volume 2. Advances in Intelligent Systems and Computing, vol 1232. Springer, Singapore. https://doi.org/10.1007/978-981-15-6759-9_3
Download citation
DOI: https://doi.org/10.1007/978-981-15-6759-9_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6758-2
Online ISBN: 978-981-15-6759-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)