Back close

A Computer Vision Based Fall Detection Technique for Home Surveillance

Publication Type : Conference Proceedings

Publisher : Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2019 (ISMAC-CVB). Published In: Smys S., Tavares J., Balas V., Iliyasu A. (eds), Advances in Intelligent Systems and Computing, Springer International Publishing,

Source : In the Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2019 (ISMAC-CVB). Published In: Smys S., Tavares J., Balas V., Iliyasu A. (eds), Advances in Intelligent Systems and Computing, Springer International Publishing, Volume 1108, Cham (2019)

Url : https://link.springer.com/chapter/10.1007/978-3-030-37218-7_41

ISBN : 9783030372187

Campus : Coimbatore

School : School of Engineering

Department : Computer Science

Year : 2019

Abstract : In this modern era where the population and life expectancy are continuously increasing, the demand for an advanced healthcare system is increasing at an unprecedented rate. This paper presents a novel and cost-effective fall detection system for home surveillance which uses a surveillance video to detect the fall. The advantage of the proposed system is that it doesn’t need the person to carry or wear a device. The proposed system uses background subtraction to detect the moving object and marks it with a bounding box. Furthermore, few rules are based on the measures extracted from the bounding box and contours around the moving object. These rules are used with the transitions of a finite state machine (FSM) to detect the fall. It is done using the posture and shape analysis with two measures viz height and speed of falling. An alarm is sent when the fall is confirmed. The proposed approach is tested on three datasets URD, FDD and multicam. The obtained results show that proposed system works with an average accuracy of 97.16% and excels the previous approaches.

Cite this Research Publication : K. Vinaya Sree and Dr. Jeyakumar G., “A Computer Vision Based Fall Detection Technique for Home Surveillance”, In the Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2019 (ISMAC-CVB). Published In: Smys S., Tavares J., Balas V., Iliyasu A. (eds), Advances in Intelligent Systems and Computing, vol. 1108. Springer International Publishing, Cham, 2019.

Admissions Apply Now