The lateral line organ of fish has inspired engineers to develop flow sensor arrays— dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisation algorithms for ALLs. Differences in the studied domain, sensor sensitivity axes, and available data prevent a fair comparison between these algorithms from their original works. We compare them with our novel quadrature method (QM), which is based on a geometric property specific to 2D-sensitive ALLs. We show how the area in which each algorithm can accurately determine the position and orientation of a simulated dipole source is affected by (1) the amount of training and optimisation data, and (2) the sensitivity axes of the sensors. Overall, we find that each algorithm benefits from 2D-sensitive sensors, with alternating sensitivity axes as the second-best configuration. From the machine learning approaches, an MLP required an impractically large training set to approach the optimisation-based algorithms’ performance. Regardless of the data set size, QM performs best with both a large area for accurate predictions and a small tail of large errors.@en

Deep learning has enabled the rapid expansion of computer vision tasks from image frames to video segments. This paper focuses on the review of the latest research in the field of computer vision tasks in general and on object localization and identification of their associated pixels in video frames in particular. After performing a systematic analysis of the existing methods, the challenges related to computer vision tasks are presented. In order to address the existing challenges, a hybrid framework is proposed, where deep learning methods are coupled with domain knowledge. An additional feature of this survey is that a review of the currently existing approaches integrating domain knowledge with deep learning techniques is presented. Finally, some conclusions on the implementation of hybrid architectures to perform computer vision tasks are discussed.@en

The majority of computer vision architectures are developed based on the assumption of the availability of good quality data. However, this is a particularly hard requirement to achieve in underwater conditions. To address this limitation, plenty of underwater image enhancement methods have received considerable attention during the last decades, but due to the lack of a commonly accepted framework to systematically evaluate them and to determine the likely optimal one for a given image, their adoption in practice is hindered, since it is not clear which one can achieve the best results. In this paper, we propose a standardized selection framework to evaluate the quality of an underwater image and to estimate the most suitable image enhancement technique based on its impact on the image classification performance.@en