Naive bayes for naive geometry: classifying vessels from length and beam

Salerno E.

Ship classification  SAR images  Maritime surveillance 

This report is concerned with the application of a Naive Bayes classification method to the identification of ship types in moderate-resolution SAR images. After a brief presentation of the principles behind the method, a simple implementation and an extensive experimentation on naive geometrical features extracted from a few thousands of targets in the OpenSARShip data set are presented. All the ship chips extracted are derived from IW GRD Sentinel 1 C-band SAR images, accompanied by AIS and MarineTraffic ground-truth data. The ideal performance of this Naive Bayes is evaluated through the standard classification indices, with respect to the ship types that are sufficiently represented in the subsets considered.

Source: ISTI Working papers, 2021