Hurdles Avoiding Assistant for Visually Impaired

This project will be developed for the visually impaired people to live their life in an easy and efficient way.  Real-time hurdles detection with distance along with voice alert is a difficult task. The modern computer technology also creates such chances to help the visually impaire

2025-06-28 16:27:44 - Adil Khan

Project Title

Hurdles Avoiding Assistant for Visually Impaired

Project Area of Specialization Artificial IntelligenceProject Summary

This project will be developed for the visually impaired people to live their life in an easy and efficient way.  Real-time hurdles detection with distance along with voice alert is a difficult task. The modern computer technology also creates such chances to help the visually impaired by detecting hurdles along with voice alert by understanding their surroundings. Visually impairment is a commonly increasing issue worldwide. We are proposing an integrated machine learning system that will allow a blind victim to identify and classify real-time based common day-to-day objects. This system will take input from the camera and then the camera will store the captured images and will send it to an android based hurdles avoiding assistant where it will identify hurdles from captured images and calculate the distance of that hurdle from the visually impaired person. If the blind person is too close to a hurdle that can cause harm or something bad, then it will generate an audio signal for the identified hurdles into an audio output by using a text-to-speech library. In this way, visually impaired persons will be prevented from accidents and identify the objects in front of them. Our project will help the visually impaired person to avoid hurdles that those people are facing in our daily life.

Project Objectives

The main objective of this project is to develop a real time hurdle detection and classification system to assist visually impaired to move safely by avoiding hurdles, in indoor and outdoor environments by using android application based hurdles avoiding assistant with camera. Our system will be reliable and easy to use. our objective is to process and analyze the camera taken pictures using machine learning in real time. Detect and recognize objects in front of visually impaired. Design and build an alarm system to inform the victim about the hurdle using voice alerts.

Project Implementation Method

Initially, we will try to implement real time object detection using machine learning tools. Different algorithm and API of deep learning will be used in our project for object detection. We will train our model for object detection on custom dataset and the dataset which is not already collected like local objects of Pakistan. For object detection we will use different equipment in our project, which includes smart phone, laptop, camera and GPU to train the model for object detection. GPU is not available in our university without GPU our model is not train which is required to complete our project. Next we will calculate the distance from the hurdle to the camera that will set on the head of the visually impaired people using OpenCV. Next we will design an alarm system for avoiding hurdles using certain python libraries. Then we will design an android application. At the end we will build a connection of camera with the android application based hurdles avoiding assistant which assist the visually impaired people to avoid the hurdles.

Benefits of the Project Technical Details of Final Deliverable Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Others Core Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Industry, Innovation and Infrastructure, Partnerships to achieve the GoalRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 69548
Camera Equipment11889918899
GPU Equipment14909949099
Document Miscellaneous 115501550

More Posts