Real Time Object Detection Using YOLO v3 Tiny with Voice Feedback for Visually Impaired

Object Detection is a technique of Computer Vision in which a software system can detect, situate and trace the object from a given image or video. The object's location is identified by drawing a bounding box around the object which is to be identified. In the proposed project we will use this object detection methodology to assist the visually impaired to locate and identify things in their surroundings. This is achieved by using the You Only Look Once (YOLO v3 Tiny) algorithm which is trained on COCO Dataset, TensorFlow, and Open CV. Then the labeled text of the identified object is converted to audio with the help of Google Text TO Speech. Multiple frames are captured by the camera on raspberry pi continuously and then they are translated into voice output. The results thus obtained will help the visually impaired to perceive their environment.