Utilizing computer vision for creating new smart
technologies can significantly improve the practical applications
of a system. This project explores several concepts in image processing,
including object detection and object classification. A NVIDIA Jetson Nano
Device is utilized to demonstrate the basics of Computer Vision. Python,
TensorFlow, Keras, and OpenCV are used to work with trained networks. The
networks for recognizing specific objects are trained to utilize YOLO, a
network with Deep Learning algorithms. This project aims to construct an
experience for a consumer, optimizing these concepts into a smart technology
‘product’.