Scribd
Upload
123 views

Automatic Braking System Using Machine Learning: (Abstract by 19SW27 and 19SW115)

The document describes an automatic braking system using machine learning that can detect obstacles in front of a vehicle and apply the brakes to avoid collisions. A camera and ultrasonic sensor would detect obstacles and an AI model would classify them as vehicles, pedestrians, or other objects. The model output would instruct a microcontroller to apply the vehicle's brakes as needed based on the obstacle type and distance. This system aims to improve road safety through more accurate braking than ultrasonic sensors alone.

Uploaded by

Milton
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
123 views

Automatic Braking System Using Machine Learning: (Abstract by 19SW27 and 19SW115)

The document describes an automatic braking system using machine learning that can detect obstacles in front of a vehicle and apply the brakes to avoid collisions. A camera and ultrasonic sensor would detect obstacles and an AI model would classify them as vehicles, pedestrians, or other objects. The model output would instruct a microcontroller to apply the vehicle's brakes as needed based on the obstacle type and distance. This system aims to improve road safety through more accurate braking than ultrasonic sensors alone.

Uploaded by

Milton
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Automatic Braking System using Machine Learning

(Abstract by 19SW27 and 19SW115)

Supervisor: Sir Zubair Sangi


Co-supervisor: Sir Parkash Sargani
Sustainable Development Goal: Goal 3: Good Health and Well-being (Road Safety
Considerations)
Abstract:
Automatic braking may be a safety technology that automatically activates the vehicle’s brake, to
the point,when necessary. Systems can vary from pre-charging brakes to slowing the vehicle to
reduce damage. Nowadays, some advanced and updated systems completely take over and stop
the vehicle before a collision happens. An automatic braking system is an important and crucial
part of safe technology for automobiles, which allows the vehicle to automatically slow down, or
in emergency case; completely stop, prior to any collision with another vehicle, pedestrian, or an
obstacle of some sort.
This can be achieved by either adding an ultrasonic wave emitter on the front side of the
automobile, or a more technical and autonomous way can be applied; machine learning.
Ultrasonic wave emitters can be a little less accurate because of it being incapable of determining
whether the obstacle is an ongoing vehicle or a tree or a normal human being, thus an AI model
is predicted to be more accurate in terms of classification and braking.
By adding a camera on the front of the vehicle, we can get a live stream of the front obstacles.
Using OpenCV and deep learning, we can easily detect any kind of obstacle, whether it is a
human, a car/bike or anything. That data is fed to the microcontroller attached, which in return
applies the necessary action based on the output of the model. For the sake of accuracy, a small
wave emitter can be added to measure the distance between the automobile and the obstacle.

Keywords: ADAS, Obstacle Detection, OpenCV, Deep Learning, Microcontroller.

Workflow Diagram:

1. Camera data is processed using OpenCV


2. Data is fed as input to the model
3. Model provides output as the obstacle if present otherwise nothing.
4. That output is fed to microcontroller (the vehicle) to act accordingly.

You might also like