Assisting Blind People Using Object Detection with Vocal Feedback
This work addresses the challenge of independent movement and safety for blind people in daily activities, though it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of assisting visually impaired individuals by detecting objects in real-time video using a YOLO model and providing vocal feedback, achieving excellent results as measured by mean Average Precision (mAP) compared to previous approaches.
For visually impaired people, it is highly difficult to make independent movement and safely move in both indoors and outdoors environment. Furthermore, these physically and visually challenges prevent them from in day-today live activities. Similarly, they have problem perceiving objects of surrounding environment that may pose a risk to them. The proposed approach suggests detection of objects in real-time video by using a web camera, for the object identification, process. You Look Only Once (YOLO) model is utilized which is CNN-based real-time object detection technique. Additionally, The OpenCV libraries of Python is used to implement the software program as well as deep learning process is performed. Image recognition results are transferred to the visually impaired users in audible form by means of Google text-to-speech library and determine object location relative to its position in the screen. The obtaining result was evaluated by using the mean Average Precision (mAP), and it was found that the proposed approach achieves excellent results when it compared to previous approaches.