• Mohammed Shoeb
• C Ramesh Kumar Reddy

Detecting suspicious activity in public places has become an important task as the number of shootings, knife attacks, terrorist attacks, and other incidents in public places around the world has increased. This paper focuses on using deep learning techniques for identifying suspicious activities in videos using 3D Convolution Neural Networks. We present the architecture of our system, which can process video footage from cameras in real time and predict whether or not the activity is suspicious, in an educational environment. Deep learning techniques are used to identify suspicious or normal activity and send an emergency message signals to the corresponding authority, if a doubtful act is identified. Frequent Monitoring is happening through consecutive frames extricated from surveillance clips. Initially the work involves, extricating the video clips into frames and preprocess them; secondly the data is trained using 3D CNN model, to predict the suspicious activity in a video footage. We also propose future developments in the area of suspicious act detection in a video footage

3DCNN Algorithm, video surveillance, Human recognition Technique, Deep Learning

"Intelligent Video surveillance through Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 2, page no.d567-d576, February-2022, Available :http://www.jetir.org/papers/JETIR2202374.pdf

"Intelligent Video surveillance through Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 2, page no. ppd567-d576, February-2022, Available at : http://www.jetir.org/papers/JETIR2202374.pdf