Khatry, R; Thompson, A (2021) Good practice in training set preparation for marine navigation systems. NPL Report. MS 33

Preview

Text (NPL Report MS 33) MS33.pdf - Published Version Download (1MB) | Preview

Abstract

The automation of navigation systems for marine vessels has been gaining momentum recently. Such systems require the ability to perform object detection on images received by the vessel’s sensors, which in turn requires machine learning models and training data. This document addresses good practice in training set preparation for these object detection algorithms. We give an overview of a typical marine navigation system and describe the accompanying object detection task. We highlight three main areas of good practice: data transferability, data coverage and data accuracy, and we give concrete recommendations on good practice.

Item Type:	Report/Guide (NPL Report)
NPL Report No.:	MS 33
Subjects:	Mathematics and Scientific Computing > Numerical Computation
Divisions:	Data Science
Identification number/DOI:	10.47120/npl.MS33
Last Modified:	11 Jan 2022 11:26
URI:	http://eprintspublications.npl.co.uk/id/eprint/9305

Actions (login required)

View Item