Deep Learning Based Audio Assistive System for Visually Impaired People

Vision impairment is a latent problem that affects numerous people across the globe. Technological advancements, particularly rise of computer processing abilities like Deep Learning (DL) models and emergence wearables pave way for assisting visually-impaired persons. The developed earlier specifically work effectually on single object detection in unconstrained environment. But, real-time scenarios, these systems are inconsistent providing effective guidance people. In addition to detection, extra information about location objects scene essential Keeping this mind, current research presents an Efficient Object Detection Model with Audio Assistive System (EODM-AAS) using DL-based YOLO v3 model aim article construct can provide detailed description around presented involves multi-label detection. Besides, determines position finally generates audio signal notify order validate performance method, simulation analysis was conducted four datasets. results established produces effectual outcome over existing methods.