Smart Parking System

Training_dataset
Output
Object_Detection_2
Object_Detection_1

Inspiration

Car parking is a major problem in urban areas in both developed and developing countries. Following the rapid incense of car ownership, many cities are suffering from lacking car parking areas with an imbalance between parking supply and demand which can be considered the initial reason for metropolis parking problems. This imbalance is partly due to ineffective land use planning and miscalculations of space requirements during the first stages of planning. Shortage of parking space, high parking tariffs, and traffic congestion due to visitors in search of a parking place are only a few examples of everyday parking problems.

What it does

We aim to create an application that monitors parking slots via the camera placed in the areas and shows the accurate parking slot availability for cars.

Before entering a particular street, we can know the parking availability in that place.

How we built it

To find empty/available parking space from the input images of the parking area, we divide the problem statement into two parts-

To obtain locations of parking spots in the images i.e which areas of the image correspond to parking spots. These locations will be used for subsequent images in the 3rd step.

For new input images, identify car instances and their locations in the parking lot and determine the occupancy using the reference locations as described in previous sections.

Challenges we ran into

We couldn't get 100% accuracy for our software as we couldn't get more datasets to train our model due to the lockdown.

Accomplishments that we're proud of

We were able to develop software that would detect empty spaces in parking areas.

What's next for Smart Parking System

We are planning to extend this application from organization-level parking monitoring to city-level parking.

We are also planning to come up with an option to find your car once it is parked in a spot.

We are also planning to notify the user(person who parks the vehicle), the time and parking slot of the car that has been parked by detecting the number plate of the respective car. (This is for security purposes in case of theft).

We will be creating a mobile application so that the users could book a parking slot before their arrival.