Remote Hyperspectral Imaging Acquisition and Characterization for Marine Litter Detection

Abstract

This paper addresses the development of a remote hyperspectral imaging system for detection and characterization of marine litter concentrations in an oceanic environment. The work performed in this paper is the following: (i) an in-situ characterization was conducted in an outdoor laboratory environment with the hyperspectral imaging system to obtain the spatial and spectral response of a batch of marine litter samples; (ii) a real dataset hyperspectral image acquisition was performed using manned and unmanned aerial platforms, of artificial targets composed of the material analyzed in the laboratory; (iii) comparison of the results (spatial and spectral response) obtained in laboratory conditions with the remote observation data acquired during the dataset flights; (iv) implementation of two different supervised machine learning methods, namely Random Forest (RF) and Support Vector Machines (SVM), for marine litter artificial target detection based on previous training. Obtained results show a marine litter automated detection capability with a 70–80% precision rate of detection in all three targets, compared to ground-truth pixels, as well as recall rates over 50%.

Litter Detection with Deep Learning: A Comparative Study

“…Nowadays, litter is one of the greatest challenges [ 1 ], due to its ubiquity, nature and scale, with dire consequences not only for freshwater and marine ecosystems [ 2 , 3 , 4 , 5 ], but also, arguably, for urban environments and human health. For example, plastic items can cause lethal damage to aquatic and terrestrial species through entanglement, gut perforation, and starvation [ 6 ].…”

Using a UAV Thermal Infrared Camera for Monitoring Floating Marine Plastic Litter

“…We defined delta as the DN difference of the target surface pixels and water surface pixels, to evaluate the TIR signal from plastic floating on water, as follows: delta(target) = DN(target) − DN(water). (6) In the field, we used 1-min averages of 1-Hz measurements (DN and delta) following the baseline surface radiation network (BSRN) [29]. On the recommendation of Kelly et al [28], the FLIR camera was powered up at least 30 min before launch, and its recording minute was taken after the UAV had been in position above the targets for at least five minutes (to maximize the stabilization of the FLIR camera).…”

“…To date, most progress has been made in the remote sensing of plastic macro litter (>5 mm) in the visible (VIS), nearinfrared (NIR), and short-wave infrared (SWIR) wavelengths. Spectral light reflectance measurements of floating plastic macro litter have been made in situ [5,6], from unmanned aerial vehicles (UAVs) [6][7][8], airplanes [6,9], and the Sentinel-2 satellite [7,8,10,11]. Another recent approach is imaging floating plastic litter with VIS and applying automated image recognition techniques using an RGB (red-green-blue) camera mounted on a bridge [12], vessel [13,14], or aircraft [15].…”

Review on the Application of Hyperspectral Imaging Technology of the Exposed Cortex in Cerebral Surgery

“…In this sense, HSI is a natural extension of color (RGB) imaging. HSI has the advantage of acquiring two-dimensional images over a wide range of the electromagnetic spectrum and has numerous practical applications, including Oceanic exploration ( Freitas et al, 2021 ; Wang, 2021 ), food quality and safety organizations ( Lohumi, 2018 ; Kim et al, 2022 ), disaster monitoring ( Farhadi et al, 2022 ), remote sensing ( Abdulridha et al, 2019 ), and agriculture ( Lu, 2020 ).…”