Abstract: The people who are having complete blindness or low vision face many types of hurdles in performing every day routine works. Blindness can occur due to many reasons including disease, injury or other conditions that limit vision. Our aim is to develop a navigation aid for the blind and the visually impaired people. We design and implement a smart cap which helps the blind and the visually impaired people to navigate freely by experiencing their surroundings. The scene around the person will be captured by using a NoIR camera and the objects in the scene will be detected. The headset will give a voice output describing the detected objects. The architecture of the system consists of Raspberry Pi 3 processor, NoIR camera, headset and a power source. The processor collects the frames of the surroundings and convert it to voice output. The device uses TensorFlow API, opensource machine learning library developed by the Google Brain Team for the object detection and classification. TensorFlow helps in creating machine learning models capable of identifying and classifying multiple objects in a single image. Thus, details corresponding to various objects present within a single frame are obtained using TensorFlow API. A Text to Speech Synthesiser (TTS) software called eSpeak is used for converting the details of the detected object (in text format) to speech output. So the video captured by using the NoIR camera is finally converted to speech signals and thus narration of the scene describing various objects is done. Objects which come under different classes like mobiles, vase, person, vehicles, couch etc are detected.
Keywords: Raspberry Pi 3 processor, TensorFlow API, TTS, eSpeak, NoIR camera, Ultrasonic sensor.
| DOI: 10.17148/IJIREEICE.2020.8520