Indoor navigation system based on computer vision using CAMShift and D* algorithm for visually impaired

Abstract

Visually impaired suffers from having a hard time to navigate to their destination with just the use of canes. Many researches have been created to provide the visually impaired the ability to navigate freely but they usually have comfortability problem as their system requires many devices to be worn. In this paper, the researchers provides a navigation system that allows the visually impaired to navigate indoor and get to their destination by only wearing a Bluetooth headset. The Bluetooth headset is used for two way communication between the visually impaired and the system. The system uses Continuously Adaptive Mean-Shift (CAMShift) algorithm to detect the visually impaired, obstacles and destination with image processing and D* algorithm to determine the shortest path required to get into the destination. The system also uses voice recognition for the input of the visually impaired. The system has been able to provide an effective and more comfortable way of navigation system for the visually impaired.