ROAD

R.O.A.D is a desktop application which will provide a deeper insight to image processing, computer vision and will enabling different aspects of lane detection and improving the results using ML. Humans while driving have a disadvantage of not always being attentive (whether it be changing th

Project Title

ROAD

Project Area of Specialization

Artificial Intelligence

Project Summary

R.O.A.D is a desktop application which will provide a deeper insight to image processing, computer vision and will enabling different aspects of lane detection and improving the results using ML.

Humans while driving have a disadvantage of not always being attentive (whether it be changing the radio or of being tired etc.) while a computer, if trained, can always be fully attentive at detecting lanes.

Project Objectives

R.O.A.D will collect the data from the mounted front view camera and applying image processing and object detection to distinguish lanes, vehicles and alert the driver. R.O.A.D will provide a deeper insight to image processing and computer vision and enabling different aspects of lane detection and improving the results. The end goal objective of this project is to:

• Train and process different data sets for lane detection. 
• Improving the image processing and lane detection process. 
• Providing real time lane and object detection.

Project Implementation Method

R.O.A.D will collect the data from the mounted front view camera and applying image processing and object detection to distinguish lanes, vehicles and alert the driver. The overall scope of the project includes

• Image capturing
• Image processing(edge detection, noise redution)
• Python(openCV, numpy)

Then the preprocessed frames will be fed to a trained model which will implement lane detection.

Output with detected road and lanes will be shown.

Benefits of the Project

 It is mainly needed by anyone who drives. As it would benefit those who are not attentive while driving as it would detect lanes on the road.

Technical Details of Final Deliverable

A desktop application will be made using pyGUI or Tkinter (a python based GUI framework).

It will prompt the user to either upload a prerecorded video (for simplification or take live input [extended scope]). Once the video is uploaded or live video captured, the preprocessing stage begins which breaks the video feed into frames and those frames fed to a trained machine learning model which detects lanes on the road.

It will make use of python based frameworks for image processing like openCV, tensor flow, numpy and pandas.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

IT

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com