AI-powered Real-Time Social Distance Monitoring System with Immutable Data Storage
A robust model that uses advanced deep learning techniques (YOLO v2) to monitor social-distancing violations at any given place in real time. The model also uses a blockchain-based data integrity validation tool to remove the risk of data tampering.
Problem Statement
To slow the spread of COVID-19, a tamper-proof, trustworthy, and privacy-enabled detection system is required to track and maintain social distancing. However, current systems in place lack consistent contact tracing, contain privacy concerns, and are vulnerable to corrupted data.
Solution
This project establishes a social distancing detection model that records contact tracing data about certain locations with crowds, as well as distances between individuals. A blockchain-based data integrity validation tool has also been added to mitigate some of the concerns of with the use of AI technology, through a hybrid on and off-chain system. Information from this application is stored to a blockchain ledger to preserve data integrity and remove the risks of data tampering, or corruption. This data can be used for analytics to detect locations vulnerable to future outbreaks and enable swift action to enforce social-distancing guidelines in these areas.
How it works
