360-degree Image Processing on NVIDIA Jetson Nano

Abstract

A wide field of vision is required for autonomous electric vehicles to operate object-detecting systems. By identifying objects, it is possible to imbue the car with human intelligence, similar to that of a driver, so that it can recognize items and make decisions to prevent collisions with them. Using a 360-degree camera is a wonderful idea because it can record events surrounding the car in a single shot. Nevertheless, 360º cameras produce naturally skewed images. To make the image appear normal but have a bigger capture area, it is required to normalize it. In this study, NVIDIA Jetson Nano is used to construct software for 360-degree image normalization processing using Python. To process an image in real-time, first choose the image shape mapping that can give information about the entire item that the camera collected. Then, choose and apply the mapping. Using Python on an NVIDIA Jetson Nano, the author of this research has successfully processed 360-degree images for local and real-time video as well as image geometry modifications.