Image-based fall detection and classification of a user with a walking support system

Abstract

The classification of visual human action is important in the development of systems that interact with humans. This study investigates an image-based classification of the human state while using a walking support system to improve the safety and dependability of these systems. We categorize the possible human behavior while utilizing a walker robot into eight states (i.e., sitting, standing, walking, and five falling types), and propose two different methods, namely, normal distribution and hidden Markov models (HMMs), to detect and recognize these states. The visual feature for the state classification is the centroid position of the upper body, which is extracted from the user’s depth images. The first method shows that the centroid position follows a normal distribution while walking, which can be adopted to detect any non-walking state. The second method implements HMMs to detect and recognize these states. We then measure and compare the performance of both methods. The classification results are employed to control the motion of a passive-type walker (called “RT Walker”) by activating its brakes in non-walking states. Thus, the system can be used for sit/stand support and fall prevention. The experiments are performed with four subjects, including an experienced physiotherapist. Results show that the algorithm can be adapted to the new user’s motion pattern within 40 s, with a fall detection rate of 96.25% and state classification rate of 81.0%. The proposed method can be implemented to other abnormality detection/classification applications that employ depth image-sensing devices.

Keywords

fall detection / walking support / hidden Markov model / multivariate analysis

References

[1] Alami R, Albu-Schaeffer A, Bicchi A, Safe and dependable physical human-robot interaction in anthropic domains: State of the art and challenges. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Beijing: IEEE, 2006

[2] Bedaf S, Gelderblom G J, De Witte L. Overview and categorization of robots supporting independent living of elderly people: What activities do they support and how far have they developed. Assistive Technology, 2015, 27(2): 88–100

[3] WHO. Good Health Adds Life to Years. Global Brief for World Health Day 2012. 2012. Retrieved form http://www.who.int/ageing/publications/whd2012_global_brief/en/

[4] Stevens J A, Thomas K, Teh L, Unintentional fall injuries associated with walkers and canes in older adults treated in US emergency departments. Journal of the American Geriatrics Society, 2009, 57(8): 1464–1469

[5] Noury N, Fleury A, Rumeau P, Fall detection-principles and methods. In: Proceedings of 29th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society. Lyon: IEEE, 2007:

[6] Tong L, Song Q, Ge Y, HMM-based human fall detection and prediction method using tri-axial accelerometer. IEEE Sensors Journal, 2013, 13(5): 1849–1856 doi:10.1109/JSEN.2013.2245231

[7] Huynh Q T, Nguyen U D, Irazabal L B, Optimization of an accelerometer and gyroscope-based fall detection algorithm. Journal of Sensors, 2015, 2015: 452078http://dx.doi.org/10.1155/2015/452078

[8] Bourke A K, Lyons G M. A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor. Medical Engineering & Physics, 2008, 30(1): 84–90

[9] Auvinet E, Multon F, Saint-Arnaud A, Fall detection with multiple cameras: An occlusion-resistant method based on 3-D silhouette vertical distribution. IEEE Transactions on Information Technology in Biomedicine, 2011, 15(2): 290–300

[10] Hirata Y, Hara A, Kosuge K. Motion control of passive intelligent walker using servo brakes. IEEE Transactions on Robotics, 2007, 23(5): 981–990

[11] Taghvaei S, Kosuge K. HMM-based state classification of a user with a walking support system using visual PCA features. Advanced Robotics, 2014, 28(4): 219–230

[12] Stone E E, Skubic M. Fall detection in homes of older adults using the Microsoft Kinect. IEEE Journal of Biomedical and Health Informatics, 2015, 19(1): 290–301

[13] Wang Y, Wu K, Ni L M. WiFall: Device-free fall detection by wireless networks. IEEE Transactions on Mobile Computing, 2016, 16(2): 581–594

[14] Daher M, El Najjar M E B, Khalil M. Automatic fall detection system using sensing floors. International Journal of Computing and Information Sciences, 2016, 12(1): 75–82

[15] Purwar A, Un Jeong D, Chung W Y. Activity monitoring from real-time triaxial accelerometer data using sensor network. In: Proceedings of International Conference on Control, Automation and Systems. Seoul: IEEE, 2007, 2402–2406

[16] Aguilar P A, Boudy J, Istrate D, A dynamic evidential network for fall detection. IEEE Journal of Biomedical and Health Informatics, 2014, 18(4): 1103–1113

[17] Shi G, Chan C S, Li W J, Mobile human airbag system for fall protection using MEMS sensors and embedded SVM classifier. IEEE Sensors Journal, 2009, 9(5): 495–503

[18] Zhao K, Jia K, Liu P. Fall detection algorithm based on human posture recognition. In: Pan J S, Tsai P W, Huang H C, eds. Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, Vol 64. Cham: Springer, 2017, 119–126

[19] Hsieh C Y, Liu K C, Huang C N, Novel hierarchical fall detection algorithm using a multiphase fall model. Sensors (Basel), 2017, 17(2): 307

[20] Perry J T, Kellog S, Vaidya S M, Survey and evaluation of real-time fall detection approaches. In: Proceedings of 6th International Symposium on High-Capacity Optical Networks and Enabling Technologies. Alexandria: IEEE, 2009, 158–164

[21] Rougier C, Meunier J, St-Arnaud A, Fall detection from human shape and motion history using video surveillance. In: Proceedings of 21st International Conference on Advanced Information Networking and Applications Workshops. Niagara Falls: IEEE, 2007, 875–880

[22] Taghvaei S, Jahanandish M H, Kosuge K. Autoregressive moving average hidden Markov model for vision-based fall prediction—An application for walker robot. Assistive Technology, 2017, 29(1): 19–27

[23] Skubic M, Harris B H, Stone E, Testing non-wearable fall detection methods in the homes of older adults. In: IEEE 38th Annual International Conference of Engineering in Medicine and Biology Society. IEEE, 2016, 557–560

[24] Hirata Y, Hara A, Kosuge K. Motion control of passive intelligent walker using servo brakes. IEEE Transactions on Robotics, 2007, 23(5): 981–990

[25] Mazhelis O. One-class classifiers: A review and analysis of suitability in the context of mobile-masquerader detection. South African Computer Journal, 2007, 36: 29–48

[26] Yamato J, Ohya J, Ishii K. Recognizing human action in time-sequential images using hidden Markov model. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 1992

[27] Goswami A, Peshkin M A, Colgate J E. Passive robotics: An exploration of mechanical computation. In: Proceedings of IEEE International Conference on Robotics and Automation. Cincinnati: IEEE, 1990, 279–284

[28] Hirata Y, Komatsuda S, Kosuge K. Fall prevention control of passive intelligent walker based on human model. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice: IEEE, 2008, 1222–1228

[29] Gonzalez R C, Woods R E. Image Processing. Digital Image Processing. Upper Saddle River: Addison-Wesley Publishing Co., Inc., 1977

[30] Rencher A C. Methods of Multivariate Analysis. 2nd ed. New York: John Wiley & Sons, 2003

[31] Rabiner, L, Juang B. An introduction to hidden Markov models. IEEE ASSP Magazine, 1986, 3(1): 4–16

Acknowledgement

The experiments were conducted with the help of Dr. Ryushiro Kawazoe, who is an experienced physical therapist and CEO of Kumasuma Inc., Dr Takuro Hatsukari from the Paramount Bed Company, Tokyo 136-8670, Japan, and the members of the System Robotics Laboratory, Tohoku University, Japan.

RIGHTS & PERMISSIONS

2018 Higher Education Press and Springer-Verlag GmbH Germany