VAIS: A Dataset for Recognizing Maritime Imagery in the Visible and Infrared Spectrums

Mabel M. Zhang, Jean Choi, Kostas Daniilidis, Michael T. Wolf, Christopher Kanan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2015, pp. 10-16

The development of fully autonomous seafaring vessels has enormous implications to the world's global supply chain and militaries. To obey international marine traffic regulations, these vessels must be equipped with machine vision systems that can classify other ships nearby during the day and night. In this paper, we address this problem by introducing VAIS, the world's first publicly available dataset of paired visible and infrared ship imagery. This dataset contains more than 1,000 paired RGB and infrared images among six ship categories - merchant, sailing, passenger, medium, tug, and small - which are salient for control and following maritime traffic regulations. We provide baseline results on this dataset using two off-the-shelf algorithms: gnostic fields and deep convolutional neural networks. Using these classifiers, we are able to achieve 87.4% mean per-class recognition accuracy during the day and 61.0% at night.