Deep Learning-Based Real-Time Object Detection in Inland Navigation

Abstract

International audience; Semi-autonomous and fully-autonomous systems must have knowledge about the objects in their environment to ensure a safe navigation. Modern approaches implement deep learning techniques to train a neural network for object detection. This project will study the effectiveness of using several promising algorithms such as Faster R-CNN, SSD, and different versions of YOLO, to detect, classify, and track objects in near real-time fluvial domain. Since no dataset is available for this purpose in literature, we first started by annotating a dataset of 2488 images with almost 35 400 annotations for training the convolutional neural network architectures. We made this data set openly accessible for the community working on this area. The other contribution of this research is the adaptation and the configuration of deep learning techniques used in other domains such as maritime and road domain to fluvial domain for autonomous vessels in which high accuracy and fast processing are vital. Experiments demonstrated that detecting objects in such environment is plausible in near real time with the selected algorithms.