Intelligence Monitoring System

Project Title

Intelligence Monitoring System

Project Area of Specialization Artificial IntelligenceProject Summary

With the recent rise and popularization of Machine Learning and Deep Learning techniques, the potential to build Intelligent systems that accurately recognize face features became a closer reality. Intelligence Monitoring System is a combination of different functionalities. Here, you will get a basic definition that captures the essence of what an Intelligence monitoring system is and what it does. After the breakout of the worldwide pandemic COVID-19, there arises a severe need of protection mechanism. Affecting the health and lives of masses, COVID-19 has called for strict measures to be followed in order to prevent the spread of disease specially in schools, offices and other working places. Closing of institutes is not the accurate solution but we can create a mechanism that assure the safety of individuals. Along with this issue we have focused on another issue in our project. The traditional manual attendance system wastes time over students’ responses. The main goal of this project is to assist any educational institute by implementing all ways necessary for the safety of the student. This project presents a real-time face-detection, face mask detection and temperature checking of students before entering in institute. This system will be used for student class attendance through automatic student identification as well. The algorithm for the system was based on analyzing facial properties and features in order to perform face detection for checking students’ attendance in real time. Our system will detect the student first and recognize the face of the student with mask and without mask then it will check the temperature of the student and save the student attendance and its temperature with current date and time in database of an application which will be accessible to administration of the institute. For student attendance we will design a complete database first which will contain the images and of all registered students therefore at run-time our system will match each student face with pre-define database and mark its attendance. It will then monitor that students are following basic safety principle or not by recognizing the presence of a mask and by checking the temperature of the student.Face detection is one of the applications of object detection and can be used in many areas like security, biometrics, law enforcement and more. There are many detector systems developed around the world and being implemented but no such system is designed yet that offers all these functionalities. Intelligence Monitoring System is a complete system that can be used for student safety as well as their attendance. This system is not limited to educational institutes, it can be implemented in offices, industries and hospitals as well for the attendance as well as for the safety measurements of the staff.

Project Objectives

• The main objective of this project is to assist any educational institute by implementing all ways necessary for the safety of the student.
• To prevent people from acquiring the coronavirus, respiratory or infectious pathogen, and blocking larger particles from sneezes or coughs of asymptomatic people, face-covering with surgical or face masks is mandatory in crowded places such as office buildings, hospitals, public transportation facilities, and restaurants.
• Its leading-edge facial recognition solution with mask detection and temperature checking can quickly identify and track each and every student in a crowd as they move about and simultaneously help recognize unfamiliar person and person who are not wearing masks and restrict access.
• With the help of facial recognition, it will be easier to track down any burglars, thieves, or other trespassers.
• A facial recognition is a module capable of matching a human face from a digital image or a video frame against a database of faces, typically employed to authenticate users through ID verification services, works by pinpointing and measuring facial features with database image.
• Recent advances in automated face analysis, pattern recognition, and AI have made it possible to develop automatic face recognition systems to address the application.
• To reduce the time that is consumed when attendance is taken manually. Unlike the manual process, an online system easily helps management to analyze student's attendance details as per requirement.
• To monitor that students are following this basic safety principle.
• As attandance is an important element in our project and attandance is a necessary element for students therfore it'll be an edge point for us as there's no need to creat a physical hurdle for student for checking SOP's.
• Each student will approach our system for attandance and their mask and temperature will be checked like-wise.

Project Implementation Method

Main Modules:

Our project consists of three main modules:

• Face Detection.
• Face Mask Detection.
• Temperature Checking.

1.    Face Detection-Methodology:

All Face detection is a computer vision technology being used in a variety of applications that identifies human faces in digital images. HAAR Cascade Haar-like features are digital image features used in object recognition. They owe their name to their intuitive similarity with Haar wavelets and were used in the first real-time face detector. Among the many possible approaches, we have decided to use a combination of knowledge-based methods for the face detection part and the neural network approach for the face recognition part.

1.    Face Mask Detection-Methodology:

For the face mask detection module, we will train a dataset that will consist of 5000 total images out of which 2500 will be masked faces and the other 2500 will be unmasked faces. The proportion of masked to unmasked faces determines that the dataset is balanced.

1.    Temperature Checking-Methodology:

An integrated sensors platform for non-contact temperature monitoring is proposed in this work. The adopted solution, based on the combined integration of an infrared thermometer and a capacitive humidity sensor, can provide a fast and accurate tool for remotely sensing both ambient and body temperature in the framework of pandemic situations, such as COVID-19, thus avoiding any direct contact with people. That’s why for the temperature checking, we will use contactless IR Temperature sensor MLX 90614. The distance range of sensor data transmission for open space without obstructions of 67 meters and enclosed space with a barrier of 13 meters.

Implementation:

• The Intelligence monitoring system can be implemented in entrance of both institute and class-room.
• It will first detect the presence of the person and later it will detect the face mask and check the temperature.
• After detecting a person, it will detect and recognize the student's face and compare it with the trained dataset that contains images of all registered students.
• If the student's face matches with the trained dataset it will mark its attendance.
• After the face recognition and attendance process, an Intelligence monitoring system will check the safety measurements.
• It will detect face masks and if no mask is detected on student's faces it will generate an alarm.
• After mask detection, it will check the temperature of the student by the contactless temperature sensor.
• After checking all safety measurements, it will store all the information of students in specific fields including Student Attendance, Wearing masks, and temperature along with the current date and time.
• After all measurements it will allow the student to enter in the institute.

Benefits of the Project

• It is a complete system that will assure student safety as well as time effectiveness.
• With the help of facial recognition, it will be easier to track down any burglars, thieves, or other trespassers.
• It’s a wide range of high-quality products that meet the needs of global customers, from facial recognition terminals that all integrate with mask detection and temperature checking. With an emphasis on quality, technology, and cost-effectiveness, it seeks to offer the best solution in a wide range of dimensions.
• Security guards and paramedical staff has to perform manual identification of a person, its mask and temperature checking that took too much time and did not boast high accuracy and most importantly this process is highly risky and it cost many lives. But our system is completely independent in the identification and sops checking process and will not only takes few seconds but is also incredibly accurate.
• Our system will be cost-effective. Attendance system using facial recognition is not yet implemented in all educational institutes due to its cost.
• A system with this technology is more expeditious, convenient, and reliable in monitoring mask-wearers and passers-by trying to access the restricted areas. The solution is flexible and easy for people to deploy.
• The other biometric attendance methods waste time as the students have to make a queue to touch their thumb on the scanning device. So, an automated attendance system using face recognition is the efficient one for student attendance.
• The facial recognition and non-contact features facilitate mask detection without touching. It not only crucial for the students and workers but also minimization of potential product minimization.
• This system can be implemented in educational institutes, offices, industries, and hospitals for the daily attendance of students and staff and to check safety measurements.
• Monitoring body temperature, even when the person is healthy, can help detect disease early and help to know if it's okay to go to work or school.
• In the era of constant cyber-attacks and advanced hacking tools, companies need a technology that would be both secure and fast. Considering that facial recognition is almost instant, it grants a quick and efficient verification of a person. Besides, it’s hard to fool this technology so this is another bonus.
• Detection with Computer Vision, significantly reducing the FAR.
• Mask detection is a simple solution to help reduce the risk of getting infected, and also a good reminder to wear masks before entering crowded areas.
• The process of recognizing a face, checking temperature, and detecting a face mask takes a few seconds and it is incredibly beneficial for the companies.
• It is a wide range of high-beneficial and time needed product.

Technical Details of Final Deliverable

Hardware Part:

Raspberry-Pi:

To implement such project, we have chosen a Raspberry Pi model 4B+.

Raspberry-Pi Camera:

We will use 6mm Wide Angle Lens, an add-on for the Raspberry pi High Quality Camera.

MLX-90614:

For the temperature checking we will use contactless IR Temperature sensor MLX 90614.

Software Part:

Raspbian OS, Visual Studio , Android Studio , Firebase.

Technical Details:

• Our system will contain the Raspberry Pi, LCD display, 6mm Raspberry pi Camera lens, temperature sensor, cables and power input and output and final prototype with sustainable connections.
• The prototype will be placed in entrance of institute and outside the classroom.
• The power supply will be taken from a wall plug and these are the only input and output from the box. On the software part, Raspbian OS is used as the operating systems for Raspberry Pi.
• Next, we will install Python, OpenCV library and other supporting libraries for the algorithm implementation of face detection.
• To train the faces into the library, we will use the “train.py” algorithm in the OpenCV library. The training data will be loaded into the script.
• We will store images of students in our database.
• These trained images will be used for the identification of students.
• In run time the system will compare the faces of the students with trained dataset and mark their attendance by generating Student_Status.xml file which will be accessible in our application.
• The next stage is implementation of face mask detection module.
• We will use a Computer Vision algorithm to detect if a person is wearing a face mask while acquiring and analyzing face data. 
• We will train dataset of 5000 images including 2500 masked and 2500 unmasked and split our dataset into three parts: training dataset, test dataset and validation dataset.
• We will use 80% of the dataset as the training data and the remaining 20% as the testing data, which makes the split ratio as 0.8:0.2 of train to test set. Out of the training data, we will use 20% as a validation data set. Overall, 64% of the dataset will be used for training, 16% for validation and 20% for testing.
• The next stage is implementation of temperature checking module.
• We will use contactless IR Temperature sensor MLX 90614 for temperature checking. It can operate on both 3V and 5V.
• We will code this sensor using raspberry pi and will use raspberry pi build in wifi module for sending sensor values in our database.
• Face Mask status and temperature of each student will also be stored in Student_Status.xml file.
• The final step of our FYP is implementation of application. We will develop 2 desktop-based or web based user-friendly applications using Visual studio depending upon the resources.
• One for checking and managing student attendance and other as a front-end interface of Intelligence monitoring system.
• We will integrate all the modules and test the final product in the end.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Education , Medical , Health , Security Core Technology Artificial Intelligence(AI)Other Technologies NeuroTechSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	46300
Raspberry-pi 4B	Equipment	1	17000	17000
Raspberry Pi 6mm Camera Lens	Equipment	1	5000	5000
Raspberry-pi Charger	Equipment	1	1000	1000
Raspberry-pi SanDisk Micro SD Card	Equipment	1	1200	1200
Ethernet Cable	Equipment	1	300	300
Pi-Case	Equipment	1	1800	1800
Camera Body	Equipment	1	2000	2000
7 inch HDMI capacitive touch LCD	Equipment	1	8000	8000
Project Prototype	Miscellaneous	1	5000	5000
Project Poster/Standie	Miscellaneous	1	2000	2000
Digital IR Temperature Sensor Module	Equipment	1	3000	3000