Scribd
Upload
99 views3 pages

The Application of Ai in Parking Management System

The document discusses using AI and computer vision in an automated parking management system. Specifically, it mentions using object detection models trained on license plate and vehicle datasets to identify vehicles and guide them to open parking spots. This system could help reduce time spent finding parking and improve the efficiency of parking lot operations. The system would use sensors at each spot to monitor occupancy and direct drivers to available spaces.

Uploaded by

Trần Xuân
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
99 views3 pages

The Application of Ai in Parking Management System

The document discusses using AI and computer vision in an automated parking management system. Specifically, it mentions using object detection models trained on license plate and vehicle datasets to identify vehicles and guide them to open parking spots. This system could help reduce time spent finding parking and improve the efficiency of parking lot operations. The system would use sensors at each spot to monitor occupancy and direct drivers to available spaces.

Uploaded by

Trần Xuân
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

The application of ai in parking management system

Group5: tien khiem tuyen khanh

Internal: based on the car image provide by two data we found in Kaggle
https://www.kaggle.com/andrewmvd/car-plate-detection
https://www.kaggle.com/jessicali9530/stanford-cars-dataset

So many of us do not enjoy standing in long queues waiting for the parking space to be
allotted. But now that we have computer vision technology with us, the long queues are
expected to go away pretty soon. That’s primarily because we can harness the Artificial
Intelligence technology for creating an automated parking system where one’s car is
parked automatically. This project will have two main mini projects like Number plate
recognition, vehicle identification. For the first two mentioned projects, you can use an
object detection model and train it to learn how to identify vehicle license plates and their
model. After that, use computer vision to navigate a path for the vehicle based on the IoT
identification. The next step is to scan the records.

In this report, we mention about two main factor:

1. AI Camera Parking
2. IoT

Input/Output:

Input

▫ Currently, with normal parking lots for cars, it takes a lot of time to find a parking spot,
or there is a situation where the car enters the parking lot but there is no vacant position.
This situation causes time and inconvenience for vehicles as well as parking managers.
Stemming from this situation, we have designed and built a smart car park model with an
automatic vacancy notification system. The solution is combined with many intelligent
and systematic control devices. Bring high efficiency to the entry and exit activities at the
parking lot. By using Images of different types and models of vehicles and create a
detection model to localize the car license plate'.

▫ Output:

The system uses magnetic card access control technology in combination with an
vacancy alarm device and intelligent parking guidance. With the system function to
report whether the parking lot is still in position or not, to avoid losing time when
entering and leaving the parking lot and parking quickly.

Parking solution that automatically finds the location, also known as the parking
guidance system, the basement space alarm system. This is a solution applied to the
basement of many parking lots of buildings, apartments, and offices today.

This system is fully automatic, using sensor technology for each location and allows
giving accurate information on the number of vacancies in each specific area and
basement. At the same time, it guides the vehicle driver to find the parking position in the
fastest way through sensors installed at each parking position.

Feature

When the driver of a vehicle is brought to the checkpoint, the driver of the car will directly manage
information about the parking position, the status, the empty space is not shown through the electronic
board located at the checkpoint.

Attribute

After that, based on this display, the operator can advise and guide the driver to be put in the empty
vehicle for the most convenience.

Data Sources

▫ . We using two main data sources in the Kaggle is Car License Plate Detection, This
dataset contains 433 images with bounding box annotations of the car license plates
within the image. Annotations are provided in the PASCAL VOC format. And Stanford
Cars Dataset, which contains 16,185 images of 196 classes of cars. The data is split into
8,144 training images and 8,041 testing images, where each class has been split roughly
in a 50-50 split. Classes are typically at the level of Make, Model, Year, ex. 2012 Tesla
Model S or 2012 BMW M3 coupe. 3D object representations are valuable resources for
multi-view object class detection and scene understanding. Fine-grained recognition is a
growing subfield of computer vision that has many real-world applications on
distinguishing subtle appearances differences. This cars dataset contains great training
and testing sets for forming models that can tell cars from one another. Data originated
from Stanford University AI Lab (specific reference below in Acknowledgment section).

You might also like