• Ketaki Santosh Raorane
• Shivani Sandesh Ware
• Amar Rajendra Palwankar

In the human less surveillance ,there is need to act to forbidden acts as early as possible .Hence deep learning based system provides the relief to the above mentioned problem.This project deals with the design approach of Real-Time Security System using deep learning on Raspberry Pi. It is focused on developing a security system that detects suspicious activities such as chasing, fighting, etc and immediately responds by sending captured image to the drop box and sending real time alerts to concern. The proposed system presents the idea of monitoring a particular place and sensing the activities that is being carrying out by the persons or objects. The proposed system offers intelligent detection of forbidden acts in near real time and also records the act in cloud hence there is no way to manipulate or destroy the image.

Raspberry Pi, Camera module, drop box, CNN, LSTM, NLP, pytorch framework, python.

"Intelligent Security System using Cloud Computing on Raspberry pi", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.143-144, March-2019, Available :http://www.jetir.org/papers/JETIR1903276.pdf

"Intelligent Security System using Cloud Computing on Raspberry pi", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp143-144, March-2019, Available at : http://www.jetir.org/papers/JETIR1903276.pdf