Real time embedded system for object detection using deep learning
Bashra Kadhim Oleiwi, Mais R. Kadhim · AIP conference proceedings · 2022
Blind people face difficulty in practicing their daily life safely because they cannot know the objects surrounding them and this exposes them to many dangers. Given that the number of blind people around the world is a significant number, this research deals to build an intelligent system that helps the blind people to know the objects surrounding them in an internal environment where it is formed. The system consists of two parts, the first part is the software, which depends on the use of one of the deep learning algorithms and its name is YOLO (You Only Look Once). This algorithm was chosen because of its high speed and accuracy, and this is what this group of people needs, which the research aims to help them as much as possible. The algorithm was trained on a ready-made dataset called COCO (Common Objects in COntex) Dataset which It is used for the purposes of discovering objects and detecting faces … etc. The other part of the system is the part of the hardware, which mainly depends on a fast and lightweight microprocessor, which is Raspberry Pi B3, in addition to the headphone and Raspberry Pi camera. After the images is taken by the Raspberry Pi Camera, these images are send to the Raspberry pi and the YOLO algorithm detect the objects in each image, and after the object is detected, it sends the output that is converted into sound via the head Phone to the person and thus can avoid the things surrounding them.