Author : Devisahay Mishra 1
Date of Publication :8th March 2018
Abstract: In this paper, an image based fall detection system for elder person who alone at home is introduced. It is novel computer vision based fall detection system using deep learning method to analyse posture in smart home environment. First, background subtraction is employed to extract the foreground human body. Then global local features of human body postures are extracted by HOG (Histogram of Oriented Gradient) and HAAR extractor. After deep learning classifier applied for posture classification. After that certain rules are set to detect falls. Experimental result indicate that the proposed method can realizes human fall detection.
Reference :
-
- Adel Rhuma,Miao Yu and Jonathon Chanbers,”Posture recognition Based Fall Dtection System”,Lectures Notes on Software Engineering, Vol.1,No.4 November 2013.J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68-73.
- Pengming Feng,Miao Yu,Syed Mohsen Naqvi,Jonathon A. Chambers,”Deep Learning for Posture Analysis in Fall Detection”,Proceedings of the 19th International Conference on Digital Signal Processing 20-23 August 2014.K. Elissa, “Title of paper if known,” unpublished.
- Yoosuf Nizan,Mohd Norzani Haji Mohd,M. Mahadi Abdul Jamil,”Human Fall Detection from Depth Images using Position and Velocity of Subject,2016 IEEE International Symposium on Robotics anmd Intelligent Sensors,IRIS 2016,17-20 December 2016,Tokyo,Japan.
- Zoran Zivkovic,”Improved Adaptive Gaussian Mixture Model for Background Subtraction”,In Proc.ICPR,2004
- Ning Jia,”Detecting Human Falls with a 3-axis Digital Accelerometer”In 20 August 2017.
- Navneet Dalal and Bill Triggs,”Histograms of Oriented Gradient for Human Detection”,INRIA Rhone-Alps,655 avenue de l’Europoe, Montbonnot 38334,france.
- Markus D.Solbach and John K. Tsotsos,”Vision Based Fallen Person Detection for the Elderly”,Department of Electrical Engineering and Computer Science York University Canada,15 August 2017.