Detection and monitoring agent

Project Title

Detection and monitoring agent

Project Area of Specialization Artificial IntelligenceProject Summary

As public concern about crime and illegal activity increases, the importance of public security is growing, and video surveillance systems are increasingly widespread tools for monitoring, management, and law enforcement in public areas. The problem is to bring automation in tracking and detecting of a person in places and, gives the location of a person with respect to time.

The detecting and monitoring of people is done through multiple cameras. There are many commercial and open source visual surveillance systems available in the market but humans manually observe the video. The goal of this research to bring automation in tracking and detecting of a person and, gives the location of a person with respect to time. This research guarantees the security of the places. This research can be implemented in different scenarios with respect to place and policy

As public concern about crime and illegal activity increases, the importance of public security is growing, and video surveillance systems are increasingly widespread tools for monitoring, management, and law enforcement in public areas. The detecting and monitoring of people is done through multiple cameras. There are many commercial and open source visual surveillance systems available in the market but humans manually observe the video. The goal of this research to bring automation in tracking and detecting of a person and, gives the location of a person. This research guarantees the security of the places

Limitations in the ability of humans to vigilantly monitor video surveillance live footage led to the demand for artificial intelligence that could better serve the task. Humans watching a single video monitor for more than twenty minutes lose 95 percent of their ability to maintain attention sufficient to discern significant events. Given that many facilities have dozens or even hundreds of cameras, the task is clearly beyond human ability. While video surveillance cameras proliferated with great adoption by users ranging from car dealerships and shopping plazas to schools and businesses to highly secured facilities such as nuclear plants, it was recognized in hindsight that video surveillance by human officers (also called ”operators”) was impractical and ineffective. Extensive video surveillance systems were relegated to merely recording for possible forensic use to identify someone, after the fact of a theft, arson, attack or incident. Where wide angle camera views were employed, particularly for large outdoor areas, severe limitations were discovered even for this purpose due to insufficient resolution. So after creating the A.I CCTV cameras it will resolve all these problems and it will detect every agent and monitor is activities.

This project covers the security of different places with help of automatic surveillance of people in that place. Therefore it is for the place which required security.

Project Objectives

Industry Objectives

An Intelligent Video Surveillance system basically censored the performance, happenings, or changing information usually in terms of human beings, vehicles or any other objects from a distance by means of some electronic equipment (usually digital camera). The scopes like prevention, detection, and intervention which have led to the development of real and consistent video surveillance systems are capable of intelligent video processing competencies. In broad terms, advanced video-based surveillance could be described as an intelligent video processing technique designed to assist security personnel’s by providing reliable real-time alerts and to support efficient video analysis for forensic investigations

Research Objectives

Based on the previous work on single detection using single stationary camera, we extend the concept to enable the tracking of multiple object detection under multiple cameras and also maintain a security-based system by multiple cameras to track person in indoor environment, to identify by my proposal system which consist of multiple cameras to monitor a person. Present study mainly aims to provide security and detect the moving object in real time video sequences and live video streaming. Based on a robust algorithm for human body detection and tracking in videos created with support of multiple cameras

Academic Objectives

The main goal of intelligent surveillance consists in providing security systems with the skills required for correctly detecting and analyzing events in monitored environments. Since these environments are complex and the information is distributed through them, the use of agent-based approaches has become more and more popular when monitoring moving objects. Agents deployed by means of this platform implement a behavior-based model that is flexible enough to deal with the challenges that monitored environments pose.

Project Implementation Method

Artificial intelligence for video surveillance utilizes computer software programs that analyze the audio and images from video surveillance cameras in order to recognize humans, vehicles, objects and events. The artificial intelligence camera sends an alert if it detects an agent who is doing anything illegal. The A.I. program functions by using machine vision. Machine vision is a series of algorithms, or mathematical procedures, which work like a flow-chart or series of questions to compare the object seen with hundreds of thousands of stored reference images of humans in different postures, angles, positions and movements. There are two types of A.I security we can use to develop our CCTV camera self-awareness robot which will detect every agent and monitor that agent:

1) Rule based A.I

A human programmer must set rules for all of the things for which the user wishes to be alerted. This is the most prevalent form of A.I. for security. Many video surveillance camera systems today include this type of A.I. capability. In this we will use a technique by bringing many CCTV expert operators and then we will see how they analyze agent in every image, video and incidents. what they abstract from every incident how they control it and how they do everything.so we will collect all this data from all the expert operators and we will train our CCTV camera according to that data and we will create rules that how it will detect and monitor the agent by himself.in this way we will not require human operator any more. It will automatically notify about every agent.

2) nonrule based A.I also called ”behavioral analytics”

This software is fully self-learning with no initial programming input by the user or security contractor. In this type of analytics, the A.I. learns what is normal behavior for people, vehicles, machines, and the environment based on its own observation of patterns of various characteristics such as size, speed, reflectivity, color, grouping, vertical or horizontal orientation and so forth. The A.I. normalizes the visual data, meaning that it classifies and tags the objects and patterns it observes, building up continuously refined definitions of what is normal or average behavior for the various observed objects. After several weeks of learning in this fashion it can recognize when things break the pattern. When it observes such anomalies it sends an alert EXAMPLE: Tracking agents in crowds is a specific case of the more general problem of multiple object tracking. Multiple object means the distribution of objects in the scene and their dynamics will be nonlinear and non-Gaussian. One of the most popular technique for nonlinear, non-Gaussian Bayesian state estimation is the particle filter or sequential Monte Carlo method. The particle filter technique is also known as CONDENSATION. To use a particle filter we need to define objects based on shape, appearance models or features.

Benefits of the Project

Direct Customers/Beneficiaries of the Project

To track individual at large populated areas such as shopping malls, educational institutes, bus stops, railway stations, air ports, sea ports. Various law enforcement agencies to investigate crimes. This will help them to trace the location of agent easily

Outputs Expected from the Project

We will be able to detect, monitor and track suspicious persons to prevent crimes. If the crime occurs in a blind place our system will predict the place by using previous detection and by using smart algorithms. The self-automated surveillance system will reduce the human efforts and cost.

In any institution, students are allowed to enter into the institute but a Visitor or a non-staff member can be a thread to university or any other institution. Therefore, in entrance there will be a detection of such non recognized person is done through this research and then monitoring of that person

In public places like shopping mall except the staff everyone is unknown and in the entrance we can select/detect particular person as a target for the monitoring the movement of that target. Also the time of a person which is marked as a target in a specific area of mall can be calculated.

This research is also applicable and useful in places where only permitted person can go. For example only few staff of hospital are allowed to enter in newly born baby wards. Let suppose if someone enters in that award with not good intention, with this project we can detect his entry in award and keep monitoring that one so the staff can catch him/her. This is one example of this scenario, other example is security required laboratory.

Technical Details of Final Deliverable

Limitations in the ability of humans to vigilantly monitor video surveillance live footage led to the demand for artificial intelligence that could better serve the task. Humans watching a single video monitor for more than twenty minutes lose 95 percent of their ability to maintain attention sufficient to discern significant events. Given that many facilities have dozens or even hundreds of cameras, the task is clearly beyond human ability. While video surveillance cameras proliferated with great adoption by users ranging from car dealerships and shopping plazas to schools and businesses to highly secured facilities such as nuclear plants, it was recognized in hindsight that video surveillance by human officers (also called ”operators”) was impractical and ineffective. Extensive video surveillance systems were relegated to merely recording for possible forensic use to identify someone, after the fact of a theft, arson, attack or incident. Where wide angle camera views were employed, particularly for large outdoor areas, severe limitations were discovered even for this purpose due to insufficient resolution. So after creating the A.I CCTV cameras it will resolve all these problems and it will detect every agent and monitor is activities. It will be working 24/7 and it will first detect agent using it’s A.I algorithms.it will detect his motion its activities and it will give number to every agent if there are multiple agents. It will give alert every time when there is any agent trespassing any area or any agent doing any harmful thing in public like any agent in crowd have weapon it will detect the agent and analyze his location with different cameras. It will give the exact location of agents by using particle algorithm. Police Chapter 4. Development Approach 11 will catch the agent easily. One of the most powerful features of the system is that a human officer or operator, receiving an alert from the A.I., could immediately talk down over outdoor public address loudspeakers to the agent. The security officer would describe the actions of the agent so that the agent had no doubt that a real person was watching them. The officer would announce that the agent was breaking the law and that law enforcement was being contacted and that they were being video-recorded. It will also save many people from harmful agent.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	65000
CCTV	Equipment	4	7500	30000
server	Equipment	1	35000	35000