Real-Time Object Detection for Visually Challenged People
Sunit Vaidya, Naisha Shah, Niti Shah, Radha Shankarmani
Abstract
One of the most important senses for a living is vision. Millions of people living in this world deal with visual impairment. These people encounter difficulties in navigating independently and safely, facing issues in accessing information and communication. The objective of the proposed work is to change the visual world into an audio world by notifying the blind people about the objects in their path. This will help visually impaired people to navigate independently without any external assistance just by using the real-time object detection system. The application uses image processing and machine learning techniques to determine real-time objects through the camera and inform blind people about the object and its location through the audio output. Inability to differentiate between objects has led to many limitations to the existing approach which includes less accuracy and low-performance results. The main objective of the proposed work is to provide good accuracy, best performance results and a viable option for the visually impaired people to make the world a better place for them.