Obstacle avoidance using stereo vision and depth maps for visual aid devices

Autor: P. Natarajan, Vaibhav Bansal, Krithika Balasubramanian
Rok vydání: 2020
Předmět:
Zdroj: SN Applied Sciences. 2
ISSN: 2523-3971
2523-3963
DOI: 10.1007/s42452-020-2815-z
Popis: Comprehending the environment accurately and proficiently is one of the fundamental undertakings for the visually impaired. Many electronic travel aid devices are utilizing stereo vision techniques. However, there is no existing technology that helps to fulfill the requirements of the visually impaired and be economical at the same time. All the current technologies are implemented only for a specific purpose and have some constraints. In this paper, we propose a new framework that integrates the critical aspects of stereo vision with some additional features for aiding the visually impaired to solve their existing problems efficiently. In this system, both stereo vision and ultrasonic sensors have been integrated to get a precise awareness of the obstacles present in the real-time surroundings. The central concept is to categorize point vertices for the detection of objects in three-dimensional space according to height, width and slope of the adjacent vertices present in the images captured by CCD cameras. The intended assistive system serves to be more cost-effective for the visually impaired with the usage of CCD cameras and low-budget sensors. The assistive system in its recognition phase employs the proposed obstacle detection algorithm using stereo vision to recognize and track impediments that are at a farther distance. While, it employs ultrasonic sensors to detect obstacles present at shorter distances. The system also overcomes the problem of finding holes and descending stairs, faced by devices that use monoscopic vision. Additional features, like the Buzzer, GPS, Voice module, Alert message, are being incorporated. The principle intention of this paper is to contribute our knowledge to assist the visually impaired to become independent and help them to adapt to various daily situations.
Databáze: OpenAIRE
Externí odkaz: