Adel Rhuma, Miao Yu, Jonathon A Chambers
(Advanced Signal Processing Group, Dept. of Electronic and Electrical Engineering, Loughborough University, Loughborough, Leicester LE11 3TU, UK)
Abstract：In this paper, we propose an efficient fall detection system in enclosed environments based on single Gaussian model using the maximum likelihood method. Online video clips are used to extract the features from two cameras. After the model is constructed, a threshold is set, and the probability for an incoming sample under the single Gaussian model is compared with that threshold to make a decision. Experimental results show that if a proper threshold is set, a good recognition rate for fall activities can be achieved.
Key words：humans fall detection; enclosed environments; one class support vector machine (OCSVM); imperfect training data; shape analysis; maximum likelihood (ML); background subtraction; codebook; voxel person
CLD number： TP391 Document code： A
Article ID： 1674-8042(2012)02-0123-06 doi： 10.3969/j.issn.1674-8042.2012.02.006
References
[1] Rajendran K P A, Corcoran B, Alwan M. Falls, fall prevention, and fall detection technologies in elder care technology for clinical practitioners.Humana Press, Totowa, USA, 2008:187-202.
[2] Noury N. A smart sensor for the remote follow up of activity and fall detection of the elderly. Proc. of the 2nd Annual International IEEE-EMB Special Topic Conference on Microtechnologies in Medicine Biology, Madison, WI, USA, 2002:314-317.
[3] LIN Chia-wen, LING Zhi-hong. Automatic fall incident detection in compressed video for intelligent homecare. Proc. of the 16th International Conference on Computer Communications and Networks, Honolulu, HI, USA, 2007: 1172-1177.
[4] Nait-Charif H, McKenna S. Activity summarisation and fall detection in a supportive home environment. Proc. of the 17th International Conference on Pattern Recognition, 2004, 4:323-326.
[5] ZHANG Tong, WANG Jue, XU Liang, et al. Fall detection by wearable sensor and one-class svm algorithm. Lecture Notes in Control and Information Science, 2006, 354: 858-863.
[6] Bourke A K, Scanaill C N, Culhane K M, et al. An optimum accelerometer configuration and simple algorithm for accurately detecting falls. Proc. of the 24th IASTED International Conference on Biomedical Engineering, ACTA Press, Anaheim, CA, USA, 2006: 156-160.
[7] Douqhty K, Lewis R, McIntosh A. The design of a practical and reliable fall detector for community and institutional telecares. Journal of Telemedicine and Telecare, 2000, 6(S1): 150-154.
[8] Almeida O, ZHANG Ming, Liu Jyh-charn, et al. Dynamic fall detection and pace measurements in walking sticks. Proc. of Joint Workshop on High Confidence Medical Devices, Software, and Systems and Medical Plug-and-Play Interoperability, Boston, MA, USA, 2007: 204-206.
[9] Bourke A K, Lyons G M. A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor. Medical Engineering Physics, 2006, 30:84-90.
[10] Bourke A, O' Brien J, Lyons G M. Evaluation of a threshold based tri-axial accelerometer fall detection algorithm. Gait-Posture, 2007, 26(2): 194-199.
[11] Chen J, Kwong K, Chang D. Wearable sensors for reliable fall detection. Proc. of the 27th Annual International Conference on Engineering in Medicine and Biology Society, Shanghai, China, 2005: 3551-3554.
[12] Clifford M A, Borras R L, Gomez L. System and method for human body fall detection. US patent 7248172, 2007.
[13] Doukas C, Maglogiannis I, Tragas P, et al. Patient fall detection using support vector machines. International Federation for Information Processing, 2007, 247:147-156.
[14] Hansen T R, Eklund J M, Sprinkle J, et al. Using smart sensors and a camera phone to detect and verify the fall of elderly persons. Proc. of European Medicine, Biology and Engineering Conference, Prague, Czech Republic, 2005, 3.
[15] Lin C S, Hsu H C, Lay Y L, et al. Wearable device for real-time monitoring of human falls. Measurement, 2007, 40(9-10): 831-840.
[16] Lord C R, Sherrington C, Menz H B, et al. Falls in older people: risk factors and strategies for prevention. Cambridge University Press, the 2nd edition, 2007.
[17] Noury N, Barralon P, Virone G, et al. A smart sensor based on rules and its evaluation in daily routines. Proc. of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Cancun-Mexico, Mexico, 2003:3286-3289.
[18] Noury N, Herve T, Rialle V, et al. Monitoring behaviour in home using a smart fall sensor and position sensors. Proc. of the 1st Annual International IEEE-EMBS Special Topic Conference on Microtechnology in Medicine & Biology, Lyon , France, 2000: 607-610.
[19] Nyan M N. Tay Francis E H, Manimaran M, et al. Garment based detection of falls and activities of daily living using 3-axis mems accelerometer. Journal of Physics: Conference Series, 2006, 34: 1059-1067.
[20] Stevens J A. The costs of fatal and non-fatal falls among older adults. Injury Prevention, 2006, 12: 290-295.
[21] Williams G, Doughty K, Cameron K, et al. A smart fall and activity monitor for telecare applications. Proc. of the 20th Annual International Conference of the Engineering in Medicine and Biology Society, Hong Kong , China, 1998, 3:1151-1154.
[22] WU Ge. Distinguishing fall activities from normal activities by velocity characteristics. Journal of Biomechanics, 2000, 33(110):1497-1500.
[23] ZHANG Tong, WANG Jue, Liu Ping, et al. Fall detection by embedding an accelerometer in cellphone and using KFD algorithm. International Journal of Computer Science and Network Security, 2006, 6(10): 277-284.
[24] Alwan M, Rajendran P, Kell S, et al. A smart and passive floor-vibration based fall detector for elderly. Proc. of the 2nd IEEE International Conference on Information and Communication Technologies: from Theory to Application, Damascus, Syria, 2006.
[25] Popescu M, Mahnot A. Acoustic fall detection using one-class classifiers. Proc. of IEEE Annual International Conference on Engineering in Medicine and Biology Society, Minneapolis, MN, USA, 2009:3505-3508.
[26] Lee M A, Tracy. An intelligent emergency response system: preliminary development and testing of automated fall detection. Journal of Telemedicine and Telecare, 2005, 11:194-198.
[27] Hazelhoff L, Han J, With P H. Video-based fall detection in the home using principal component analysis. Proc. of Advanced Concepts Intelligent Vision System, 2008, 1:298 - 309.
[28] YU Miao, Naqvi S, Chamber J. Fall detection in the elderly by head tracking. Proc. of IEEE SSP Cardiff, UK, 2009.
[29] Rougier C, Meunier J, St-Arnaud A, et al. Monocular 3D head tracking to detect falls of elderly people, engineering in medicine and biology society. Proc. of the 28th Annual International Conference of the IEEE, 2006, 3: 6384-6387.
[30] Rougier C, Meunier J, St-Arnaud A, et al. Fall detection from human shape and motion history using video surveillance. Proc. of the 21st International Conference on Advanced Information Networking and Applications Workshops, Niagara Falls, Ontario, Canada, 2007:875-880.
[31] Kim K, Chalidabhongse T, Harwood D, et al. Real-time foreground-background segmentation using code-book model. Real-Time Imaging, 2005, 11: 172-185.
[32] Kohonen T. Improved versions of learning vector quantization. Proc. of International Joint Conference on Neural Networks, San Diego CA, USA, 1990: 545-550.
[33] Ripley B D. Pattern recognition and neural networks. Cambridge University Press, the 1st ed., 1996.
[34] Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE Journal of Robotics and Automation, 1987, 3(4): 323-344.
[35] Magnus R J, Neudecker H. Matrix differential calculus with applications in statistics and econometrics. John Wiley and Son, the third ed., 2007.
[36] YU Miao, Naqvi S, Chamber J. Study of one class boundary method classifiers for application in a video-based fall detection system. Submitted to IET computer vision.
[full text view]
