Open AccessACTION RECOGNITION USING SURVEILLANCE SYSTEM
Author(s) -
Rishabh Paunikar,
Shubham Thakare,
Utkarsh Anuse,
B. W. Balkhande
Publication year - 2020
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2020.v04i12.118
Subject(s) - computer science , action (physics) , action recognition , artificial intelligence , computer vision , pattern recognition (psychology) , physics , quantum mechanics , class (philosophy)
Surveillance Systems using CCTV cameras or any other surveillance devices record the footage all the time they are active. Most of the Data recorded is idle data where no activity takes place. When an activity which has occurred is supposed to be viewed the user has to go through all of the footage to check when and what had happened. This system eases this time consuming task. It uses Action Recognition to filter the idle movement data and trims the part where activity has been recorded using movement detection and various actions. It has a prominent scope for utilization in making the process of examining the footages from surveillance systems simple. This project could be implemented at public places and could enable respective concerned departments to investigate the data at an amazingly rapid rate. Thus, in an era of increasing crimes rates, this project could be a breakthrough in untangling the evidence data and eventually assist in increasing the rate of crime resolution.[1] Keywords—Surveillance System, Surveillance, Machine Learning, Neural Networks, Action Recognition, Image detection