A New Remote Hyperspectral Imaging System Embedded on an Unmanned Aquatic Drone for the Detection and Identification of Floating Plastic Litter Using Machine Learning

Abstract

This paper presents a new Remote Hyperspectral Imaging System (RHIS) embedded on an Unmanned Aquatic Drone (UAD) for plastic detection and identification in coastal and freshwater environments. This original system, namely the Remotely Operated Vehicle of the University of Littoral Côte d’Opale (ROV-ULCO), works in a near-field of view, where the distance between the hyperspectral camera and the water surface is about 45 cm. In this paper, the new ROV-ULCO system with all its components is firstly presented. Then, a hyperspectral image database of plastic litter acquired with this system is described. This database contains hyperspectral data cubes of different plastic types and polymers corresponding to the most-common plastic litter items found in aquatic environments. An in situ spectral analysis was conducted from this benchmark database to characterize the hyperspectral reflectance of these items in order to identify the absorption feature wavelengths for each type of plastic. Finally, the ability of our original system RHIS to automatically recognize different types of plastic litter was assessed by applying different supervised machine learning methods on a set of representative image patches of marine litter. The obtained results highlighted the plastic litter classification capability with an overall accuracy close to 90%. This paper showed that the newly presented RHIS coupled with the UAD is a promising approach to identify plastic waste in aquatic environments.

A Bibliometric Analysis and Overall Review of the New Technology and Development of Unmanned Surface Vessels

“…A novel Remote Hyperspectral Imaging System (RHIS) was integrated into an Unmanned Aquatic Drone (UAD) for the purpose of detecting and identifying plastic debris in both coastal and freshwater ecosystems. The findings indicate that this newly implemented RHIS, in conjunction with the UAD, constitutes an environmentally friendly and effective method for the identification of plastic pollution in aquatic settings [97]. In the case that mobile sensors could not be deployed, the USV was taken to identify pollution sources, map the environmental impact and be an analysis tool for the further research of these ecosystems, promoting the green development of ecology [98].…”

A Deep Spectral-Spatial Residual Attention Network for Hyperspectral Image Classification

“…Each pixel in the HSI consists of a different spectrum in terms of wavelength, which relates to the material composition of the features [1]. HSI, with its high spectral resolution, has been widely used in many applications such as crop monitoring [2], [3], urban development [4], [5], the mining industry [6], [7], environmental and natural resources management [8], [9], surveillance [10], [11], etc. This paper mainly focuses on hyperspectral image classification, which intends to assign every pixel in the HSI to a specific thematic class.…”