• Snehal Mhatre
• Amit Kadam
• Rahul Kucha
• Sangita Chaudhari

alls are the leading cause of injury and death in elderly individuals. Unfortunately, fall detectors are typically based on wearable devices, and the elderly often forget to wear them.. We can reduce the impact of fall consequences, if human fall has been detected instantly and proper medical facility is provided. Our detector combines algorithms (background subtraction) as input to a machine learning algorithm with high detection accuracy. Tests conducted on the different fall videos .We present here a unique video data set which will be very useful for the community to test the fall detection.This video data set contains different falls and normal daily activities acquired in realistic conditions.The use of computer vision systems offers a solution to analyze people behavior and detect events and different falls.It is also based on the combination of motion history image and the shape of human in variation in the dataset.It provides the results on video sequences of daily activities and falls.

Fall detection,Video Sequence for fall detection,Machine Learning ,Artificial Intelligent ,Deep Learning.

"MACHINE LEARNING IN VIDEO SURVEILLANCE FOR FALL DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.242-246, April-2019, Available :http://www.jetir.org/papers/JETIR1904D33.pdf

"MACHINE LEARNING IN VIDEO SURVEILLANCE FOR FALL DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp242-246, April-2019, Available at : http://www.jetir.org/papers/JETIR1904D33.pdf