Comparing Spectral Bands for Object Detection at Sea using Convolutional Neural Networks. (October 2019)

• Record Type: Journal Article
• Authors: Stets, Jonathan D.; Schöller, Frederik E. T.; Plenge-Feidenhans'l, Martin K.; Andersen, Rasmus H.; Hansen, Søren; Blanke, Mogens
• Is Part Of: Journal of physics. Volume 1357(2019)
• Publication Date: 2019-10
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1357/1/012036
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: This study compares spectral bands for object detection at sea using a convolutional neural network (CNN). Specifically, images in three spectral bands are targeted: long wavelength infrared (LWIR), near-infrared (NIR) and visible range. Using a calibrated camera setup, a large set of images for each of the spectral bands are captured with the same field of view. The image sets are then used to train and validate a CNN for object detection to evaluate the performance in the different bands. Prediction performance is employed as a quality assessment and is put in a navigational perspective. The result is a quantitative evaluation that reveals the strengths and weaknesses of using different spectral bands individually or in combination for autonomous navigation at sea. The analysis covers two object classes of particular importance for safe navigation.