Abstract
With the increase in the number of elderly people living alone, the use of computer vision technology for real-time fall detection is of great importance. In this paper, we review fall detection based on computer vision from four perspectives: background significance, current research status, relevant influencing factors, and future research outlook. We summarized our approach by classifying the three types of input image data in fall detection systems: RGB (Red, Green, Blue), Depth, and IR (Infrared Radiation), outlining research in both target tracking and bone detection for basic image processing tasks, as well as methods for processing video data. We analyzed the possible effects of multiple factors on fall detection regarding camera selection, the individual object recognized, and the recognition environment, and collected the solutions. Based on the current problems and trends in vision-based fall detection, we present an outlook on future research and propose four new ideas including functional extensions using the easy fusion feature of Mask R-CNN (Mask Region with Convolutional Neural Network), the use of YOLO (You Only Look Once) family to improve the speed of target detection, using variants of LSTM (Long Short-Term Memory) such as GRU (Gate Recurrent Unit) to achieve more efficient detection, and using Transformer methods that have been migrated from natural language processing to computer vision for detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
WHO global report on falls prevention in older age (2007)
Gutierrez, J., Rodriguez, V., Martin, S.: Comprehensive review of vision-based fall detection systems. Sens.-Basel 21(3) (2021)
Chen, Z.J., Wang, Y.: Infrared-ultrasonic sensor fusion for support vector machine-based fall detection. J. Intell. Mater. Syst. Struct. 29(9), 2027–2039 (2018)
Msaad, S., Cormier, G., Carrault, G.: Detecting falls and estimation of daily habits with depth images using machine learning algorithms. In: 42nd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC), Montreal, Canada, pp. 2163–2166. IEEE (2020)
Yodpijit, N., Sittiwanchai, T., Jongprasithporn, M.: The development of artificial neural networks (ANN) for falls detection. In: 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), pp. 547–50. IEEE (2017)
Ramanujam, E., Padmavathi, S.: A vision-based posture monitoring system for the elderly using intelligent fall detection technique. In: Mahmood, Z. (eds.) Guide to Ambient Intelligence in the IoT Environment. Computer Communications and Networks. Springer, Cham, pp. 249–69 (2019). https://doi.org/10.1007/978-3-030-04173-1_11
Auvinet ER, C., Meunier, J., St-Arnaud, A., Rousseau, J.: Multiple cameras fall data set. Technical Report Number 1350. University of Montreal: Montreal, QC, Canada (2011)
Charfi, I.: Optimized spatio-temporal descriptors for real-time fall detection: comparison of support vector machine and Adaboost-based classification. J. Electr. Imag. 22(4) (2013)
Kepski, M., Kwolek, B.: Embedded system for fall detection using body-worn accelerometer and depth sensor. In: International Workshop Intelligent Data, pp. 755–759 (2015)
Martinez-Villasenor, L., Ponce, H., Brieva, J., Moya-Albor, E., Nunez-Martinez, J., Penafort-Asturiano, C.: UP-fall detection dataset: a multimodal approach. Sensors (Basel) 19(9) (2019)
Ma, X.: Depth-based human fall detection via shape features and improved extreme learning machine. IEEE J. Biomed. Health Inf. 18(6) (2014)
Cippitelli, E., Gambi, E., Gasparrini, S., Spinsante, S.: TST Fall detection dataset v2. IEEE Dataport (2016)
CMU Graphics Lab—Motion Capture Library (2021). http://mocap.cs.cmu.edu/
Munaro, M.: A feature-based approach to people re-identification using skeleton keypoints (2014)
Adhikari, K.: Activity recognition for indoor fall detection using convolutional neural network (2017)
Tran, T.H.: A multi-modal multi-view dataset for human fall analysis and preliminary investigation on modality (2018)
Anitha, G., Priya, S.B.: Vision based real time monitoring system for elderly fall event detection using deep learning. Comput. Syst. Sci. Eng. 42(1), 87–103 (2022)
Kong, X.B., Meng, Z.L., Nojiri, N., Iwahori, Y., Meng, L., Tomiyama, H.: A HOG-SVM based fall detection IoT system for elderly persons using deep sensor. Procedia Comput. Sci. 147, 276–282 (2019)
Zhong, C.N., Ng, W.W.Y., Zhang, S., Nugent, C.D., Shewell, C., Medina-Quero, J.: Multi-occupancy fall detection using non-invasive thermal vision sensor. IEEE Sens. J. 21(4), 5377–5388 (2021)
Feng, Z., Zhu, X., Xu, L., Liu, Y.: Research on human target detection and tracking based on artificial intelligence vision. In: 2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), pp. 1051–1054 (2021)
Velasquez, J., Piech, K., Lehnhoff, S., Fischer, L., Garske, S.: Incremental development of a co-simulation setup for testing a generation unit controller for reactive power provision. Comput. Sci. Res. Dev. 32(1–2), 3–12 (2016). https://doi.org/10.1007/s00450-016-0319-2
Satish, B., Jayakrishnan, P.: Hardware implementation of template matching algorithm and its performance evaluation. In: 2017 International Conference on Microelectronic Devices, Circuits and Systems (ICMDCS) (2017)
He, S.S., Liang, A., Lin, L., Song, T.: A continuously adaptive template matching algorithm for human tracking. In: 2017 First IEEE International Conference on Robotic Computing (IRC), pp. 303–309 (2017)
Ramirez, H., Velastin, S.A., Meza, I., Fabregas, E., Makris, D., Farias, G.: Fall detection and activity recognition using human skeleton features. IEEE Access 9, 33532–33542 (2021)
Chaaraoui, A.A., Padilla-Lopez, J.R., Florez-Revuelta, F.: Fusion of skeletal and silhouette-based features for human action recognition with RGB-D devices. In: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 91–97 (2013)
Zhang, H.B., Zhang, Y.X., Zhong, B., Lei, Q., Yang, L., Du, J.X., et al.: A comprehensive survey of vision-based human action recognition methods. Sensors (Basel) 19(5) (2019)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Ullah, A., Ahmad, J., Muhammad, K., Sajjad, M., Baik, S.W.: Action recognition in video sequences using deep bi-directional LSTM with CNN features. IEEE Access 6, 1155–1166 (2018)
Luo, H., Liao, J., Yan, X., Liu, L.: Oversampling by a constraint-based causal network in medical imbalanced data classification. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2021)
Chen, Y., Kong, X., Meng, L., Tomiyama, H.: An edge computing based fall detection system for elderly persons. Procedia Comput. Sci. 174, 9–14 (2020)
Fan, Y.X., Levine, M.D., Wen, G.J., Qiu, S.H.: A deep neural network for real-time detection of falling humans in naturally occurring scenes. Neurocomputing 260, 43–58 (2017)
Chhetri, S., Alsadoon, A., Al-Dala’in, T., Prasad, P.W.C., Rashid, T.A., Maag, A.: Deep learning for vision-based fall detection system: enhanced optical dynamic flow. Comput. Intell. 37(1), 578–595 (2020)
Kong, X., Chen, L., Wang, Z., Chen, Y., Meng, L., Tomiyama, H.: Robust self-adaptation fall-detection system based on camera height. Sensors (Basel) 19(17) (2019)
Baldewijns, G., Debard, G., Mertes, G., Croonenborghs, T., Vanrumste, B.: Improving the accuracy of existing camera based fall detection algorithms through late fusion. In: P Annual International IEEE EMBS, pp. 2667–2671 (2017)
Khraief, C., Benzarti, F., Amiri, H.: Elderly fall detection based on multi-stream deep convolutional networks. Multimed. Tools Appl. 79(27–28), 19537–19560 (2020). https://doi.org/10.1007/s11042-020-08812-x
He, K., Gkioxari, G., Doll´ar, P., Girshick, R.: Mask R-CNN. In: Facebook AI Research (FAIR) (2018)
Mobsite, S., Alaoui, N., Boulmalf, M.: A framework for elders fall detection using deep learning. IEEE (2020)
Lin, C.-B., Dong, Z., Kuan, W.-K., Huang, Y.-F.: A framework for fall detection based on OpenPose skeleton and LSTM/GRU models. Appl. Sci. 11(1) (2020)
Yin, Y., Lei, L., Liang, M., Li, X., He, Y., Qin, L.: Research on fall detection algorithm for the elderly living alone based on YOLO. In: 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT), pp. 403–408 (2021)
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO Series in 2021 (2021)
Lu, N., Wu, Y., Feng, L., Song, J.: Deep learning for fall detection: three-dimensional CNN combined with LSTM on video kinematic data. IEEE J. Biomed. Health Inform. 23(1), 314–323 (2019)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., et al.: Attention is all you need. Comput. Lang. (2017)
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al.: An image is worth 16x16 Words: transformers for image recognition at scale. Google Res. Brain Team (2021)
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Microsoft Research Asia (2021)
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., et al.: Swin transformer V2: scaling up capacity and resolution. In: Microsoft Research Asia (2022)
Acknowledgment
This work was supported by grants from the National Natural Science Foundation of China (grant no. 61977012), the China Scholarship Council (grant no. 201906995003), the Central Universities in China (grant no. 2021CDJYGRH011), and the Key Research Programme of Chongqing Science & Technology Commission (grant no. Cstc2019jscx-fxydX0054).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, M., Li, X., Liu, J., Wang, S., Liu, L. (2023). A Survey of Computer Vision-Based Fall Detection and Technology Perspectives. In: Sun, Y., et al. Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2022. Communications in Computer and Information Science, vol 1682. Springer, Singapore. https://doi.org/10.1007/978-981-99-2385-4_45
Download citation
DOI: https://doi.org/10.1007/978-981-99-2385-4_45
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2384-7
Online ISBN: 978-981-99-2385-4
eBook Packages: Computer ScienceComputer Science (R0)