Motion Compensation and Tracking using block based Motion detection


1. Urban commuter wastes about 42 hours a year stuck in traffic jams.Commuters waste about 2.9 billion gallons of fuel at the intersections.
2. Even there is no balance between the congestion on roads.
3. We aim to provide a sophisticated solution to all these issues with our proposed system.
4. Our motto includes allowing maximum concurrent vehicles to cross the intersection without having traffic lights.

Car with Controller
Car with Controller


Designing Cars and Using Neural Networks for making them Autonomous.

1. Approximately 30,000 images were collected for dataset and they were sent through a neural network with 3 convolutional networks (64, 64 and 32 filters), a max pool layer, a flattening layer and two fully connected layers having 128 neurons each.
2. It took about two and half hours for the network to produce accuracy of 98% on a laptop with 8 GB RAM.

Central Server.

1. Traffic lights were replaced with a central controller that will make the cars halt or pass through critical sections without any collisions.
2. A rudimentary scheduling algorithm was designed that would batch the cars to allow maximum cars pass through the intersection point.

Car with Controller
Car with Controller


1. The system was tested with two path schemes namely Path Scheme A and Path Scheme B (Paths are used to mimic GPS inputs) where the route of destinations was supplied to cars and the cars had 100% success rate
2.Final aim of eliminating the dependency on traffic lights was achieved collectively because of the seamless interaction between the backend server and the cars.