Design and Implementation of Autonomous Surveillance Algorithm for security system

Project Title

Design and Implementation of Autonomous Surveillance Algorithm for security system

Project Area of Specialization Artificial IntelligenceProject Summary

My main aim to work on this project is to make surveillance autonomous. This project is about making an autonomous surveillance system using a deep learning approach. My system will be able to detect and classify the moving object in a certain area of surveillance. In Today's world, it is becoming a requirement of every sector in order to mitigate the human burden and to minimize the number of surveillance personnel. In Today's world, it is a very challenging approach as this is emerging technology in security systems. It would be a very unique system and highly recommended to sensitive places such as bank lockers etc. It is becoming the need of the hour to install such systems. This will cater to the security needs of a sector or organization.

Project Objectives

1) The first objective is to do a literature review regarding autonomous systems

2) Selection of viable technique

3) The third objective of this project is to make the security system autonomous.

4) The fourth objective is to mitigate the human burden and lessen the number of surveillance personnel.

5) The fifth objective is to make the security system efficient and flexible.

6) to make an application for this

Project Implementation Method

The working mechanism of this technology is to target a certain area for surveillance. At first, the Camera stream is fed into the algorithm where it assigns a  static background with a threshold value and contour area, whenever motion is detected it will change the threshold value and display it in the frame and show the detected object with a contour around the object in another frame. On the other side with the help of a neural network (YOLOv3), it will perform classification as well and classify the moving object in the detection frame. As an indicator to show motion detection it will send an alert SMS using an application programming interface to a predefined receiver number to let the other person be aware of motion detection.

Benefits of the Project

This autonomous system has a number of advantages including mitigating the burden on patrolling and surveillance personnel, high accuracy, it will detect any moving object despite the fact that the object was present in the dataset it will still detect it and give an alert SMS. It will improve surveillance tasks.

Technical Details of Final Deliverable

1) Technique will be finalized first to make classification a real-time scenario

2) Autonomous system will be tested by implementing in campus

3) Efficiency of detection and classification will be tested

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	48000
camera	Equipment	1	6000	6000
POE switch	Miscellaneous	1	5000	5000
Nvidia Graphic Card	Equipment	1	37000	37000