Social-Distancing-Detection

About the Project

Social Distancing Alert System is Used to Detect the People who are Violating the Social Distancing as we mentioned the Distance required to mark as a Safe mark & Distance to Violate the Rules. as well as Confidence level is also an Important factor to tell the Machine on a factor of 100%, how much confidence level is Required to Identify the persons. This means it have to concentrate on Humans only not Objects. humans having the Structure and mark a centroid in each of the people and calculate the distance between the people. Based on the Euclidean Distancing Formula, we are calculating the Social Distancing.

GitHub Logo

Social Distancing Alert System Using Artificial Intelligence

Social Distancing Alert System System uses existing IP cameras and CCTV cameras combined with Computer Vision to detect if people are at a specific distance and adhere to social distancing or not.

How does it Work ?

GitHub Logo

Features of Social Distancing Alert System

  1. Multi-Channel Recognition Add multiple cameras in a few minutes and allow cameras to access the capability of AI to recognize faces.

  2. No new hardware required You don’t need new cameras to enable the platform. Instead, it can work on the existing RTSP camera and connect to your existing smart speakers.

  3. Watch Alerts Automatically when someone violates social distancing. Also, set the rate of detection of faces and sending warnings.

Where can we use Social Distancing AI App?

screen shot 2017-08-07 at 12 18 15 pm Airports screen shot 2017-08-07 at 12 18 15 pm Hospitals screen shot 2017-08-07 at 12 18 15 pm Offices
screen shot 2017-08-07 at 12 18 15 pm Manfacturing PLants screen shot 2017-08-07 at 12 18 15 pm Retail Shops screen shot 2017-08-07 at 12 18 15 pm Metro Stations
screen shot 2017-08-07 at 12 18 15 pm Public Libraries screen shot 2017-08-07 at 12 18 15 pm Schools screen shot 2017-08-07 at 12 18 15 pm Religious Places
  1. Airports Social Distancing AI App can be used at airports to identify if people are maintaining social distance or not. Multiple IP cameras installed at the airport can capture people standing in close proximity and logs are kept in a system. The app triggers the voice alerts and sends notifications to the concerned authorities.

  2. Hospitals Hospitals can use social distancing app to monitor if people are adhering to social distancing or not. Using CCTV cameras installed at hospital premises, health authorities can track if visitors, patients or health workers are maintaining a distance or not. If somebody is found violating the distancing, alerts will be sent to the concerned authorities to take action.

  3. Offices The risk of COVID-19 will be not be ending soon; therefore, offices after the lockdown can use this app to ensure that social distancing is maintained until the risk of COVID-19 does not go away. Offices can add face data of their employees and if anyone is found not following distance can receive an alert or notification.

  4. Manufacturing plants Social distancing alert device can be used in manufacturing plants to prevent workers from the risk of infection. IP or CCTV cameras installed at the plants would capture and identify if workers are found in close contact with each other. Notification alerts will be sent to the concerned workers and their authorities.

  5. Retail shops Retail stores can use the social distancing AI app to ensure that visitors maintain a specific distance from each other. Cameras connected to the app would track the in-store activity and trigger voice alert to aware people. Also, retail stores can integrate a plugin into their website or app to display the live count of visitors in the store so that people can visit the store when the count is less and there is no risk of infection.

  6. Metro Stations Metro stations are considered as the most crowded places where the social distancing AI app can help reduce the risk of COVID-19 by alerting people and concerned authorities. Cameras installed at metro stations can use the capability of AI to track the movement of people and find if everyone is maintaining the social distance or not.

  7. Public libraries Public libraries can use their existing CCTV or IP cameras to detect if visitors maintain a specific distance while sitting and reading in the library. If people are not found maintaining that distance, the system will trigger an alarm and alert people to create a gap to contain the risk of COVID-19.

  8. Schools Using a social distancing AI app, schools can manage social distancing efficiently. If students or teachers are found violating the distancing within school premises, an alert is raised and notification is sent to concerned authorities.

  9. Religious Places Religious places like temples and churches can also use the social distancing platform by using their existing cameras. If anyone is found in close contact with another person or group of persons, a voice alarm will trigger and notification will be sent to security guards or concerned authorities.

There are many flavours for doing this Project. But, I have Chosen Artificial Neural Networks ( YOLO ) to complete this project and deployed in a Flask Application.

Let us Know Something about this Project 😀

The main Concept of this Project is to unerstad how computer vision is Useful for Detecting the Social-Distnace between two persons. For this, We have Used Open CV with Python & Neural Networks to calculate the Distance between the Persons and Identifying the people who are Violating the Social distance and who are non-Violating the Social Distancing Rules. Some of the Description about the Project ahs Mentioned below: Artificial Intelligence (AI) is that wave sweeping the technology world today. If you want to join this revolution but do not have the skills yet, this series of courses are right for you.In addition to the development of machine learning that leads to new capabilities, we have subsets within the domain of machine learning, each of which offers a potential area of specialization for those interested in a career in AI.

Neural-Networks

Github Logo Neural networks are integral for teaching computers to think and learn by classifying information, similar to how we as humans learn. With neural networks,the software can learn to recognize images, for example. Machines can also make predictions and decisions with a high level of accuracy based on data inputs.

Natural-Language-Processing

Github Logo Natural language processing gives machines the ability to understand human language. As this develops, machines will learn to respond in a way a human audience can understand. In the future, this will dramatically change how we interface with all computers.

Deep-Learning

Github Logo Deep learningis at the cutting-edge of intelligent automation. It focuses on machine learning tools and deploying them to solve problems by making decisions. With deep learning, data is processed through neural networks, getting closer to how we think as humans. Deep learning can be applied to images, text, and speech to draw conclusions that mimic human decision making.

The result of this Final Flask Application will look like this.

Github Logo

We can modify or made as much as we can in that Flask Application, for looking more beautiful.

Overview of the Project

The future scope of Artificial Intelligence involves using robots to help in reducing the Man power & also do the Work In an Effecient way which is more Elagant than now. this Project may Uprises the Concepts of Self-Driving-Cars to Identify the Obstacles while taking the Curve. The computer Vision plays a vital role in Object-Detection. It can create new career paths in the field of Machine learning, Data mining, and analysis, AI software development, program management, and testing. The demand for AI certified professionals will grow along with the developments in AI.

Working Procedure of this Project 😀

Below are the System Requirements

Requirement amount Required
System RAM min. 4Gb
Python Software above version 3.7
Anaconda Software version 2.6 is Preferable
GPU min 2Gb

Python Packages need to be Installed before Performing

  • pip install opencv-python
  • pip install flask
  • pip install keras
  • pip install pandas
  • pip install matplotlib
  • pip install numpy
  • pip install scipy
  • pip install scikit-learn
  • pip install imutils
  • pip install os
  • pip install Object_detection
  • pip install packages

After Install all the Necessary Python libraries. Now, Its time launch the files in a Python Editor.

Below Python Editors is Preferable to launch this Project.

  • Anaconda ( SPYDER )
  • Python IDLE
  • Pycharm
  • Visual-Studio

Anaconda ( SPYDER ) is Preferable code Editor.

Github Logo

Thanks to HacksOverflow Hackathon for building talents and Innovations by Organising such events !

Project Done by : Venkata Sreeram