Inspiration
Smart Surveillance System for Social Good. Our inspiration was to control the crime rates which are on a hike in daily newspapers and news channels. Nowadays, Unwarranted government surveillance is an intrusion on basic human rights that threatens the very foundations of a democratic society. The Purpose is to gain confidence in government services and to maintain transparency between government and people. A major concern is for the goodness of the people.
The main motive was to contribute somewhere in the development of the nation.
What it does
The proposed system includes the specialized mechanisms for Camera Tampering, Long Time Tracking, Counting the number of peoples. An alert (siren) will be generated each time anyone tries to destroy/tamper the camera by any means.Also, an alert will be generated if someone enters the chamber by covering his/her face by any means.A mail will be sent to the nearest police station and bank admin so that immediate actions can be taken.The entire mechanism takes place in real-time, thus decreasing the time complexity to a great extent making the system an efficient mechanism to prevent any anti-social activities.The space complexity will be reduced by processing only suspicious frames of a video and storing only such videos.
How I built it
We used a combination of Machine Learning and Web Development to build the project. The Technologies used in this project are OpenCV and Flask. The primary approach for the proposed system consists of - Background Subtraction, Object Detection and Tracking, Feature Extractions, and Pattern Matching.
Challenges I ran into
The project follows a methodology of creating a system that is cost-effective and has fewer hardware requirements. Thus, without making changes to the existing system this system can be used for ATM surveillance. The main challenge the team faced was the availability of data. Since, the idea was to make the system capable of real-time video processing, at every phase of design and development, the overall cost was kept low so that the system becomes effective. One limitation was the hardware requirement(availability of GPUs) for training purposes.
Accomplishments that I'm proud of
The problem we choose was statement 4 of the hackathon which was an open problem based on the theme "Democracy".We had to brainstorm and get the idea ourselves matching with the theme and we are proud of finding a good idea and successfully developing a prototype that will contribute to the accountability and transparency of a democratic government.
What I learned
What I learned Technically is as follows- For deployment purposes, we learned the basics of Flask and integrating flask with machine learning. We learned a method to develop haar cascades. We divided our project into different modules and every one has its technical benefits.The teammate working on camera tampering learned background subtraction.The teammate working on face detection learned a way to detect person wearing mask.
What I learned Socially is as follows- Meaning of Democracy and role of people in Democracy.How security is an important part of a Democracy. As a team, we learned to work together in good coordination.There were many ups and down that we went through learning the art of handling pressure.
What's next for Third-Eye
The future scope of the project consists of the following-
• The system can be further used at various other crime locations for survelliance and crime prevention.
• It can be used in old age homes in place of panic button to identify a mishappening.
• It can be used for home survelliance.
• It can be used in farm fields for survelliance of crops.
• It can be used to avoid terrorist attacks.
• Implement it at various railway stations,airport and many more places that require security to ensure that no
malfunctioning will occur .One can also implement it at different isolated roads with some constraints to ensure
women security at night .
Log in or sign up for Devpost to join the conversation.