Artificial Intelligence based Autonomous Aerial Vehicle for Security Surveillance

Once the unusual activity is recognized the proposed system will raise the alarm to inform security personnel about the possible threats with visual and GPS coordinates. This Autonomous Aerial Vehicle (AAV) also features a live feed that can be used by security personnel if needed. Our proposed proj

Project Title

Artificial Intelligence based Autonomous Aerial Vehicle for Security Surveillance

Project Area of Specialization

Robotics

Project Summary

Today in this emerging world, Surveillance is a major issue, especially on the borders, no-go zone, sports stadiums, and sensitive sites with the rising of security threads. For this reason, we are proposing an Autonomous Aerial Vehicle (AAV) based solution with AI to monitor the defined premises for unusual activities i.e. mob gathering, human detection, etc which is also used by law enforcement, investigation, spying, search and rescue, drone journalism, photography and military reconnaissance.

Once the unusual activity is recognized the proposed system will raise the alarm to inform security personnel about the possible threats with visual and GPS coordinates. This Autonomous Aerial Vehicle (AAV) also features a live feed that can be used by security personnel if needed. Our proposed project not only can increase the mobility and coverage domain but also the cost of its operation is significantly lower than that of manned aerial vehicles (MAVs).

Likewise, this Unmanned Autonomous Aerial Vehicle (UAAV) also features a live feed that can be used by security personnel if finds him necessary. This system will ensure the safety of the security personnel without compromising the security of the sensitive areas or the border.

The waypoints are set using "Mission planner" open-source software that has a great graphic user interface (GUI) and makes it possible to change the upcoming waypoint's altitude, change the mode of flight, and can even change the direction of flight.

Project Objectives

Objectives:

Drones give you a bird’s eye view for the purpose of evaluating current security protocols. They can also become an important part of advanced security methods at your remote or urban secure site Inspections. AI-based drones rely largely on computer vision. This technology enables drones to detect objects while flying and allows the analysis and recording of information on the ground. The drone will carry a camera. Videos captured would be fed back to the ground station by radio link. The ground station/onboard records flight imagery data signal. Ground Control Station to Navigate, Control and Guide the drone as per the desired path as well monitor the health of the drone system. Security teams use drones to inspect and survey roofs, fences, and other assets. So main objectives are,

• Increase personal and property safety and security control.
• Encourage the idea of substituting human guards with robotic surveillance devices with more capabilities.
• Monitoring contaminated facilities by taking live video for security purposes.
• AI also monitors the video feed to alert for suspicious activity
• Demonstrate how to build your own security quad-copter in a simple way.

Project Implementation Method

Project Implementation:

The design of the quadcopter is discussed in detail by breaking the design down by components requirements, construction, and testing of both hardware and software parts of the project.

• Hardware Design:

The hardware design focuses on the identification of the system’s physical components and their interrelationships. Also determines how these components fit into the system architecture. It also discusses the requirements specification of actual hardware and circuit construction. The tasks involved in the design and development of the frame.

• Design considerations:

The first thing was to do a design consideration where analysis of the various parts was analyzed and the choice for the different components to use are decided.

•  Draw the block diagram:

In the design of the circuit hardware, the main blocks of the overall system and drawings are made so that we can step ahead according to the given block diagram and hardware circuitry.

•  Identify the most suitable flight board controller:

The third step was to choose a microcontroller suitable for the project implementation. To do this first determine the required hardware interfaces e.g. Flight controller? module, motors actuators, and sensors. The choice of microcontroller depends either on digital or analog functions. For serial to parallel conversion and vice versa these features are best delivered by the PixHawk 2.4.8 flight board microcontroller.

• Identify required motors and how to design them:

The fourth step in the design process was to design the layout of the motor and electronic speed controller that will be used in the construction as different motors need special circuitry and need battery eliminator circuits that are special for their use. The fifth step was to explain the Quadcopter movement mechanism.

• Phyton Script on RPi:

The fifth step is to implement a Raspberry Pi on the drone. The main purpose of pi is that use Artificial intelligence (computer vision) it is used to detect the human with the help of a camera and gimble installed on the drone. The drone will carry a camera. Videos captured would be fed back to the ground station by radio link. The ground station/onboard records flight imagery/acoustic data signal and with the help of the GPS already installed on the frame the coordinates of the target are sent to the ground station where the live stream/ monitoring is seen. For the monitoring/ streaming, we use an open-source software Ardupilot, and Mission planner for the autonomous flight and monitoring of the drone.

Benefits of the Project

Traditional observational surveillance methods are typically limited by the stationary nature of the camera. The camera is therefore usually handled manually or fixed upon a tripod or other structure. Aerial surveillance with a helicopter achieves the desired result but is also very costly. Our project provides the ideal solution to the problems and limitations faced by other surveillance methods. Drone surveillance presents an easier, faster, and cheaper method of data collection. Consequently, there are also a number of other key advantages. Drone planes can enter narrow and confined spaces, produce minimal noise, and are equipped with night-vision cameras with AI assistance. For this reason, they provide imagery that the human eye is unable to detect. Our Project's main Benefits are given below

• It quickly covers large and difficult-to-reach areas.
• Reducing staff numbers and costs and additionally do not require much space for its operations.
• AI allows drones to fly safely and perform tasks autonomously.
• They ensure situational follow-up and improve team responsiveness.
• With its pre-planned flight path, it can access any subject for Inspections.
• Autonomous drones can be used in numerous applications such in the Military, Large complexes,   Universities, Government buildings, etc
• It benefits military law enforcement and other government agencies in their mission.

Technical Details of Final Deliverable

Working Hardware able to perform the operation of Surveillance in real-time for the Human Detection having Flight Duration within 20 to 25 minutes while the drone will operate in three modes of Fly.

• Autonomous Mode:

In this mode we give coordinates of the area where we want to take a mission and give coordinates of the area so the drone does its job autonomously and if the human is detected it also gives the coordinates of that person.

•  Altitude Hold:

In altitude hold mode, the autopilot simply tries to maintain the set pressure altitude present at the time of engagement When altitude hold mode is selected, the throttle is automatically controlled to maintain the current altitude.

• Return to Launch (RTL):

RTL mode (Return To Launch mode) navigates Copter from its current position to hover above the home position. The behavior of RTL mode can be controlled by several adjustable parameters. In RTL mode the autopilot uses a barometer that measures air pressure as the primary means for determining altitude (“Pressure Altitude”) and if the air pressure is changing in your flight area, the copter will follow the air pressure change rather than actual altitude (unless you are within 20 feet of the ground.

The battery failsafe can be configured to automatically switch the vehicle into RTL, SmartRTL, or Land mode if the vehicle battery voltage drops below a specified voltage for 10 seconds or the estimated remaining capacity has dropped below a configurable threshold.

• Human Detection using AI:

Working Hardware is able to perform the operation of Surveillance in real-time for the Human Detection and give its Coordinates using GPS to the ground station.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Security

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Internet of Things (IoT), Robotics

Sustainable Development Goals

Industry, Innovation and Infrastructure, Peace and Justice Strong Institutions

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com