No 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.

Autonomous ships rely on sensory data to perceive objects of interest in their environment. Deep Learning based object detection in the image domain commonly used to solve this issue. The robustness of such approaches in non-ideal conditions is, however, still to be proven. In this work state of the art methods are applied on the RetinaNet architecture attempting to create a more robust object detection network given noisy input data. The GroupSort activation function and Spectral Normalization is used and the results are compared to the standard RetinaNet network. Our findings show that these modifications perform better and ensure robustness under moderate noise levels, than the standard RetinaNet network.

No abstract

No abstract