Automated Fall Detection Using Computer Vision

The population of elderly people is increasing day-by-day in the world. One of the major health issues of an old person is injury during a fall and this issue becomes compounded for elderly people living alone. In this paper, we propose a novel framework for automated fall detection of a person from videos. Background subtraction is used to detect the moving person in the video. Different features are extracted by applying rectangle and ellipse on human shape to detect the fall of a person. Experiments have been carried out on the UR Fall Dataset which is publicly available. The proposed method is compared with existing methods and significantly better results are achieved.

[1]  Abbes Amira,et al.  CS-based fall detection for connected health applications , 2017, 2017 Fourth International Conference on Advances in Biomedical Engineering (ICABME).

[2]  Qiang Li,et al.  Gaussian mixture model for background based automatic fall detection , 2013 .

[3]  Annupan Rodtook,et al.  Fall detection using directional bounding box , 2015, 2015 12th International Joint Conference on Computer Science and Software Engineering (JCSSE).

[4]  Lin Guan,et al.  Noise Effect and Noise-Assisted Ensemble Regression in Power System Online Sensitivity Identification , 2017, IEEE Transactions on Industrial Informatics.

[5]  Xue Wang,et al.  A novel multi-cue integration system for efficient human fall detection , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[6]  Jean Meunier,et al.  Robust Video Surveillance for Fall Detection Based on Human Shape Deformation , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Haibo Wang,et al.  Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine , 2014, IEEE Journal of Biomedical and Health Informatics.

[8]  Nirmala B Joshi,et al.  A fall detection and alert system for an elderly using computer vision and Internet of Things , 2017, 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT).

[9]  Miguel A. Labrador,et al.  Dynamic background subtraction for fall detection system using a 2D camera , 2014, 2014 IEEE Latin-America Conference on Communications (LATINCOM).

[10]  Dan Meng,et al.  Automatic fall detection of human in video using combination of features , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[11]  S. Khawandi,et al.  Applying Machine Learning Algorithm in Fall Detection Monitoring System , 2013, 2013 5th International Conference on Computational Intelligence and Communication Networks.

[12]  Irene Y. H. Gu,et al.  Human fall detection via shape analysis on Riemannian manifolds with applications to elderly care , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[13]  Nigel H. Lovell,et al.  Low-Power Fall Detector Using Triaxial Accelerometry and Barometric Pressure Sensing , 2016, IEEE Transactions on Industrial Informatics.

[14]  Senem Velipasalar,et al.  Wearable Camera- and Accelerometer-Based Fall Detection on Portable Devices , 2016, IEEE Embedded Systems Letters.

[15]  Jie Liu,et al.  A system of fall detection using a wearable device based on bluetooth communication , 2016, 2016 13th IEEE International Conference on Solid-State and Integrated Circuit Technology (ICSICT).

[16]  Benoit Gosselin,et al.  Wireless respiratory monitoring and coughing detection using a wearable patch sensor network , 2017, 2017 15th IEEE International New Circuits and Systems Conference (NEWCAS).

[17]  Mohammed Rziza,et al.  A novel approach to improve background subtraction method for fall detection system , 2015, 2015 IEEE/ACS 12th International Conference of Computer Systems and Applications (AICCSA).

[18]  Sever Pasca,et al.  Fall detection algorithm based on triaxial accelerometer data , 2013, 2013 E-Health and Bioengineering Conference (EHB).

[19]  Jiann Shing Shieh,et al.  A threshold-based algorithm of fall detection using a wearable device with tri-axial accelerometer and gyroscope , 2015, 2015 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS).

[20]  Yoong Choon Chang,et al.  Visual based fall detection through human shape variation and head detection , 2013, IMPACT-2013.

[21]  Nadia Baha,et al.  Depth camera based fall detection using human shape and movement , 2016, 2016 IEEE International Conference on Signal and Image Processing (ICSIP).

[22]  Harry W. Tyrer,et al.  Context-Aware, Accurate, and Real Time Fall Detection System for Elderly People , 2018, 2018 IEEE 12th International Conference on Semantic Computing (ICSC).

[23]  Nuth Otanasap,et al.  Pre-Impact Fall Detection Based on Wearable Device Using Dynamic Threshold Model , 2016, 2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT).

[24]  David P. Colvin,et al.  Falls In The Elderly: Detection And Assessment , 1991, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991.