Traffic sign recognition based on deep learning

Our project is about traffic sign recognition based on machine learning. In our project we detect the signs of traffics on roads by camera which is fitted on the front of camera. The system is able to work in two modes, the training mode in which a database can be built by  collectin

2025-06-28 16:29:51 - Adil Khan

Project Title

Traffic sign recognition based on deep learning

Project Area of Specialization Artificial IntelligenceProject Summary

Our project is about traffic sign recognition based on machine learning. In our project we detect the signs of traffics on roads by camera which is fitted on the front of camera.

The system is able to work in two modes, the training mode in which a database can be built by 
collecting a set of traffic signs for training and validation, and a testing mode in which the system 
can recognize a traffic sign which has not been seen before. In the training mode, a traffic sign 
image is collected by the camera and stored in the raw image database to be classified and used for 
training the system. The collected image is then sent to color segmentation process where all 
background objects and unimportant information in the image are eliminated. The generated image 
from this step is a binary image containing the traffic sign and any other objects similar to the color 
of the traffic sign. The noise and small objects in the binary image are cleaned by the object 
selector process and the generated image is then used to create or update the training image 
database.

For this purpose we make our data set of images of traffic signs by camera. Then we train this data and make model and save it. This model is used in the chip of camera which is used for detection of signs. In future this project is useful in automation vehicles, further it is useful in safe driving.

Traffic signs are an essential part of our day to day lives. They contain critical information that 
ensures the safety of all the people around us. Without traffic signs, all the drivers would be 
clueless about what might be ahead to them and roads can become a mess. The annual global roach 
crash statistics say that over 3,280 people die every day in a road accident. These numbers would 
be much higher in case if there were no traffic signs. On the other hand, researchers and big 
companies are working extensively on proposing solutions to self-driving cars. Just to name a few 
these include Tesla, Uber, Google, Audi, BMW, Ford, Toyota, Mercedes, Volvo, Nissan, etc. These 
autonomous vehicles need to follow the traffic rules and for that, they have to understand the 
message conveyed through traffic signs

Project Objectives

Traffic signs are an essential part of our day to day lives. They contain critical information that 
ensures the safety of all the people around us. Without traffic signs, all the drivers would be 
clueless about what might be ahead to them and roads can become a mess. The annual global roach 
crash statistics say that over 3,280 people die every day in a road accident. These numbers would 
be much higher in case if there were no traffic signs. On the other hand, researchers and big 
companies are working extensively on proposing solutions to self-driving cars. Just to name a few 
these include Tesla, Uber, Google, Audi, BMW, Ford, Toyota, Mercedes, Volvo, Nissan, etc. These 
autonomous vehicles need to follow the traffic rules and for that, they have to understand the 
message conveyed through traffic sign. 

Project Implementation Method

In our project we used python 3.9 for train our model, get accuracy, plottings graph and for GUI. After the train of our our model we save file with the name of "traffic.h5", this model we save can b used in chips of cameras which is for to detection of traffic signs. 

Benefits of the Project

Our project is useful in future for automation of vehicles which based on reboot system. 

The GUI which we make can be used in shopping mall for mobile apps to detection of pictures. 

This system is also can be used the in auto cars.

Technical Details of Final Deliverable

This project is used for detection of traffic signs. In a front of vehicles there is camera for the detection purpose. The signs of traffics help to robot for safe driving. If the sign of speed limit 30km/h is on road the vehicle slow down their speed up to 30km/h. Same like if the sign is to stop the car/vehicle the reboot system stop the car.

In this way our project is help full and guide the automotive vehicles and able to vehicles to fallow the traffic signs. 

Final Deliverable of the Project HW/SW integrated systemCore Industry TransportationOther Industries Manufacturing , Security Core Technology Artificial Intelligence(AI)Other Technologies RoboticsSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 35000
Smart device Equipment12500025000
Stationary Miscellaneous 225005000
Printing Miscellaneous 225005000

More Posts