TRAINING A DEEP LEARNING SYSTEM FOR MARITIME APPLICATIONS

摘要

An object detection network can be trained with training images to identify and classify objects in images from a sensor system disposed on a maritime vessel. The objects in the images can be identified, classified, and heat maps can be generated. Instructions can be sent regarding operation of the maritime vessel. For some training images, water conditions, sky conditions, and/or light conditions in the image can be changed to generate a second image.