Object detection and voice guidance for Visually Impaired persons

Object detection and voice guidance for Visually Impaired persons

ABSTRACT

Object detection plays a very important role in many applications such as image retrieval, surveillance, robot navigation, way-finding, etc. In this proposed work, an effective method to propose different approaches to detect indoor signage, stairs and pedestrians. The proposed system detects objects in the web camera frame and alerts the user about its movement by tracking objects location. When an object movement is detected a voice alarm is generated for guiding the blind persons around. The object detection is achieved by YOLO object detection model. This uses deep neural networks to learn and detect objects. The proposed work used GTTS module for text to voice conversion. This application is useful for surveillance the objects around the visually impaired people. Experimental setup shown that this system was quite fast for object detection and giving voice messages.

Advantages

Fast. Good for real-time processing.

Predictions (object locations and classes) are made from one single network. Can be trained end-to-end to improve accuracy.

YOLO is more generalized. It outperforms other methods when generalizing from natural images to other domains like artwork.

Region proposal methods limit the classifier to the specific region. YOLO accesses to the whole image in predicting boundaries. With the additional context, YOLO demonstrates fewer false positives in background areas.

YOLO detects one object per grid cell. It enforces spatial diversity in making predictions.

PROPOSED SYSTEM

• This application detection moving objects using Yolo trained model, it uses recurrent neural networks for object detection.
• The objects are identified and its co-ordinates are arrived. Comparing it with previous frames we find the object movement.
• The object class identified is converted to voice by google voice converter.
• The input is video stream from webcam.