High-Resolution Aerial Detection of Marine Plastic Litter by Hyperspectral Sensing

Development and Application of Unmanned Aerial High-Resolution Convex Grating Dispersion Hyperspectral Imager

This study presents the design and development of a high-resolution convex grating dispersion hyperspectral imaging system tailored for unmanned aerial vehicle (UAV) remote sensing applications. The system operates within a spectral range of 400 to 1000 nm, encompassing over 150 channels, and achieves an average spectral resolution of less than 4 nm. It features a field of view of 30°, a focal length of 20 mm, a compact volume of only 200 mm × 167 mm × 78 mm, and a total weight of less than 1.5 kg. Based on the design specifications, the system was meticulously adjusted, calibrated, and tested. Additionally, custom software for the hyperspectral system was independently developed to facilitate functions such as control parameter adjustments, real-time display, and data preprocessing of the hyperspectral camera. Subsequently, the prototype was integrated onto a drone for remote sensing observations of Spartina alterniflora at Yangkou Beach in Shouguang City, Shandong Province. Various algorithms were employed for data classification and comparison, with support vector machine (SVM) and neural network algorithms demonstrating superior classification accuracy. The experimental results indicate that the UAV-based hyperspectral imaging system exhibits high imaging quality, minimal distortion, excellent resolution, an expansive camera field of view, a broad detection range, high experimental efficiency, and remarkable capabilities for remote sensing detection.

Review of Methods for Automatic Plastic Detection in Water Areas Using Satellite Images and Machine Learning

Ocean plastic pollution is one of the global environmental problems of our time. "Rubbish islands" formed in the ocean are increasing every year, damaging the marine ecosystem. In order to effectively address this type of pollution, it is necessary to accurately and quickly identify the sources of plastic entering the ocean, identify where it is accumulating, and track the dynamics of waste movement. To this end, remote sensing methods using satellite imagery and aerial photographs from unmanned aerial vehicles are a reliable source of data. Modern machine learning technologies make it possible to automate the detection of floating plastics. This review presents the main projects and research aimed at solving the "plastic" problem. The main data acquisition techniques and the most effective deep learning algorithms are described, various limitations of working with space images are analyzed, and ways to eliminate such shortcomings are proposed.

Dune plants as a sink for beach litter: The species-specific role and edge effect on litter entrapment by plants

Anthropogenic litter accumulates along coasts worldwide. In addition to the flowing litter load, wind, sea currents, geomorphology and vegetation determine the distribution of litter trapped on the sandy coasts. Although some studies highlighted the role of dune plants in trapping marine litter, little is known about their efficiency as sinks and about the small-scale spatial distribution of litter across the dune area. Here, we explore these gaps by analysing six plant species widespread in Mediterranean coastal habitats, namely Echinophora spinosa, Limbarda crithmoides, Anthemis maritima, Pancratium maritimum, Thinopyrum junceum, and Salsola kali. The present study analyses for the first time the capture of litter by dune vegetation at a multi-species level, considering their morphological structure. Data on plastic accumulation on dune plants were compared with unvegetated control plots located at embryo-dune and foredune belts. We found that dunal plants mainly entrapped macrolitter (> 0.5 cm). Particularly, E. spinosa, L. crithmoides, A. maritima and P. maritimum mostly accumulated litter in the embryo dune while T. junceum and S. kali entrapped more in the foredune area. Moreover, beach litter was mainly blocked at the edge of the plant patches rather than in the core, highlighting the 'Plant-edge litter effect'. As A. maritima and S. kali entrapped respectively more litter in embryo and foredune habitats, these species could be used to monitor and recollect litter. In this light, our findings provide further insight into the role of dune plants in the beach litter dynamics, suppling useful information for beach clean-up actions.

Amsterdam urban water system as entry point of river plastic pollution

Accumulation of plastic litter in aquatic environments negatively impacts ecosystems and human livelihood. Urban areas are assumed to be the main source of plastic pollution in these environments because of high anthropogenic activity. Yet, the drivers of plastic emissions, abundance, and retention within these systems and subsequent transport to river systems are poorly understood. In this study, we demonstrate that urban water systems function as major contributors to river plastic pollution, and explore the potential driving factors contributing to the transport dynamics. Monthly visual counting of floating litter at six outlets of the Amsterdam water system results in an estimated 2.7 million items entering the closely connected IJ river annually, ranking it among the most polluting systems measured in the Netherlands and Europe. Subsequent analyses of environmental drivers (including rainfall, sunlight, wind speed, and tidal regimes) and litter flux showed very weak and insignificant correlations (r = [Formula: see text]0.19-0.16), implying additional investigation of potential drivers is required. High-frequency observations at various locations within the urban water system and advanced monitoring using novel technologies could be explored to harmonize and automate monitoring. Once litter type and abundance are well-defined with a clear origin, communication of the results with local communities and stakeholders could help co-develop solutions and stimulate behavioral change geared to reduce plastic pollution in urban environments.

Marine environmental monitoring with unmanned vehicle platforms: Present applications and future prospects

Basic monitoring of the marine environment is crucial for the early warning and assessment of marine hydrometeorological conditions, climate change, and ecosystem disasters. In recent years, many marine environmental monitoring platforms have been established, such as offshore platforms, ships, or sensors placed on specially designed buoys or submerged marine structures. These platforms typically use a variety of sensors to provide high-quality observations, while they are limited by low spatial resolution and high cost during data acquisition. Satellite remote sensing allows monitoring over a larger ocean area; however, it is susceptible to cloud contamination and atmospheric effects that subject the results to large uncertainties. Unmanned vehicles have become more widely used as platforms in marine science and ocean engineering in recent years due to their ease of deployment, mobility, and the low cost involved in data acquisition. Researchers can acquire data according to their schedules and convenience, offering significant improvements over those obtained by traditional platforms. This study presents the state-of-the-art research on available unmanned vehicle observation platforms, including unmanned aerial vehicles (UAVs), underwater gliders (UGs), unmanned surface vehicles (USVs), and unmanned ships (USs), for marine environmental monitoring, and compares them with satellite remote sensing. The recent applications in marine environments have focused on marine biochemical and ecosystem features, marine physical features, marine pollution, and marine aerosols monitoring, and their integration with other products are also analysed. Additionally, the prospects of future ocean observation systems combining unmanned vehicle platforms (UVPs), global and regional autonomous platform networks, and remote sensing data are discussed.

UAV remote sensing applications in marine monitoring: Knowledge visualization and review

With the booming development of information technology and the growing demand for remote sensing data, unmanned aerial vehicle (UAV) remote sensing technology has emerged. In recent years, UAV remote sensing technology has developed rapidly and has been widely used in the fields of military defense, agricultural monitoring, surveying and mapping management, and disaster and emergency response and management. Currently, increasingly serious marine biological and environmental problems are raising the need for effective and timely monitoring. Compared with traditional marine monitoring technologies, UAV remote sensing is becoming an important means for marine monitoring thanks to its flexibility, efficiency and low cost, while still producing systematic data with high spatial and temporal resolutions. This study visualizes the knowledge domain of the application and research advances of UAV remote sensing in marine monitoring by analyzing 1130 articles (from 1993 to early 2022) using a bibliometric approach and provides a review of the application of UAVs in marine management mapping, marine disaster and environmental monitoring, and marine wildlife monitoring. It aims to promote the extensive application of UAV remote sensing in the field of marine research.

Close-range remote sensing-based detection and identification of macroplastics on water assisted by artificial intelligence: A review

Detection and identification of macroplastic debris in aquatic environments is crucial to understand and counter the growing emergence and current developments in distribution and deposition of macroplastics. In this context, close-range remote sensing approaches revealing spatial and spectral properties of macroplastics are very beneficial. To date, field surveys and visual census approaches are broadly acknowledged methods to acquire information, but since 2018 techniques based on remote sensing and artificial intelligence are advancing. Despite their proven efficiency, speed and wide applicability, there are still obstacles to overcome, especially when looking at the availability and accessibility of data. Thus, our review summarizes state-of-the-art research about the visual recognition and identification of different sorts of macroplastics. The focus is on both data acquisition techniques and evaluation methods, including Machine Learning and Deep Learning, but resulting products and published data will also be taken into account. Our aim is to provide a critical overview and outlook in a time where this research direction is thriving fast. This study shows that most Machine Learning and Deep Learning approaches are still in an infancy state regarding accuracy and detail when compared to visual monitoring, even though their results look very promising.

Detection of River Plastic Using UAV Sensor Data and Deep Learning

Plastic pollution is a critical global issue. Increases in plastic consumption have triggered increased production, which in turn has led to increased plastic disposal. In situ observation of plastic litter is tedious and cumbersome, especially in rural areas and around transboundary rivers. We therefore propose automatic mapping of plastic in rivers using unmanned aerial vehicles (UAVs) and deep learning (DL) models that require modest compute resources. We evaluate the method at two different sites: the Houay Mak Hiao River, a tributary of the Mekong River in Vientiane, Laos, and Khlong Nueng canal in Talad Thai, Khlong Luang, Pathum Thani, Thailand. Detection models in the You Only Look Once (YOLO) family are evaluated in terms of runtime resources and mean average Precision (mAP) at an Intersection over Union (IoU) threshold of 0.5. YOLOv5s is found to be the most effective model, with low computational cost and a very high mAP of 0.81 without transfer learning for the Houay Mak Hiao dataset. The performance of all models is improved by transfer learning from Talad Thai to Houay Mak Hiao. Pre-trained YOLOv4 with transfer learning obtains the overall highest accuracy, with a 3.0% increase in mAP to 0.83, compared to the marginal increase of 2% in mAP for pre-trained YOLOv5s. YOLOv3, when trained from scratch, shows the greatest benefit from transfer learning, with an increase in mAP from 0.59 to 0.81 after transfer learning from Talad Thai to Houay Mak Hiao. The pre-trained YOLOv5s model using the Houay Mak Hiao dataset is found to provide the best tradeoff between accuracy and computational complexity, requiring model resources yet providing reliable plastic detection with or without transfer learning. Various stakeholders in the effort to monitor and reduce plastic waste in our waterways can utilize the resulting deep learning approach irrespective of location.

Operational use of multispectral images for macro-litter mapping and categorization by Unmanned Aerial Vehicle

The use of Unmanned Aerial Systems (UAS, aka drones) has shown to be feasible to perform marine litter surveys. We operationally tested the use of multispectral images (5 bands) to classify litter type and material on a beach-dune system. For litter categorization by their multispectral characteristics, the Spectral Angle Mapping (SAM) technique was adopted. The SAM-based categorization of litter agreed with the visual classification, thus multispectral images can be used to fasten and/or making more robust the manual RGB image screening. Fully automated detection returned an F-score of 0.64, and a reasonable categorization of litter. Overall, the image-based litter density maps were in line with the manual detection. Assessments were promising given the complexity of the study area, where different dunes plants and partially-buried items challenged the UAS-based litter detection. The method can be easily implemented for both floating and beached litter, to advance litter survey in the environment.

Litter Detection with Deep Learning: A Comparative Study

Pollution in the form of litter in the natural environment is one of the great challenges of our times. Automated litter detection can help assess waste occurrences in the environment. Different machine learning solutions have been explored to develop litter detection tools, thereby supporting research, citizen science, and volunteer clean-up initiatives. However, to the best of our knowledge, no work has investigated the performance of state-of-the-art deep learning object detection approaches in the context of litter detection. In particular, no studies have focused on the assessment of those methods aiming their use in devices with low processing capabilities, e.g., mobile phones, typically employed in citizen science activities. In this paper, we fill this literature gap. We performed a comparative study involving state-of-the-art CNN architectures (e.g., Faster RCNN, Mask-RCNN, EfficientDet, RetinaNet and YOLO-v5), two litter image datasets and a smartphone. We also introduce a new dataset for litter detection, named PlastOPol, composed of 2418 images and 5300 annotations. The experimental results demonstrate that object detectors based on the YOLO family are promising for the construction of litter detection solutions, with superior performance in terms of detection accuracy, processing time, and memory footprint.

Carpobrotus spp. patches as trap for litter: Evidence from a Mediterranean beach

Dunal plants may affect the patterns of deposition of beach litter. In this study, we aimed at evaluating if Carpobrotus spp. patches may act as a litter trap in coastal dune systems. To do so, we counted the number of macrolitter occurring in both Carpobrotus and control (embryo dune vegetation) patches classifying each item into categories according to the Marine Strategy. Totally, we observed a significant difference between litter trapped in Carpobrotus (331 items, representing 62.4% of the total beach litter) and control (199, 37.6%). Plastic fragments were the most trapped items by both Carpobrotus (46.2%) and control patches (47.2%). We also calculated the item co-occurrence, obtaining a random aggregated 'litter community'. The main emerging output is that Carpobrotus patches act as filter in respect to different anthropogenic materials (overall plastics), suggesting that alien plant management actions may contribute to solve beach litter issues as well.

UAV Approach for Detecting Plastic Marine Debris on the Beach: A Case Study in the Po River Delta (Italy)

Anthropogenic marine debris (AMD) represent a global threat for aquatic environments. It is important to locate and monitor the distribution and presence of macroplastics along beaches to prevent degradation into microplastics (MP), which are potentially more harmful and more difficult to remove. UAV imaging represents a quick method for acquiring pictures with a ground spatial resolution of a few centimeters. In this work, we investigate strategies for AMD mapping on beaches with different ground resolutions and with elevation and multispectral data in support of RGB orthomosaics. Operators with varying levels of expertise and knowledge of the coastal environment map the AMD on four to five transects manually, using a range of photogrammetric tools. The initial survey was repeated after one year; in both surveys, beach litter was collected and further analyzed in the laboratory. Operators assign three levels of confidence when recognizing and describing AMD. Preliminary validation of results shows that items identified with high confidence were almost always classified properly. Approaching the detected items in terms of surface instead of a simple count increased the percentage of mapped litter significantly when compared to those collected. Multispectral data in near-infrared (NIR) wavelengths and digital surface models (DSMs) did not significantly improve the efficiency of manual mapping, even if vegetation features were removed using NDVI maps. In conclusion, this research shows that a good solution for performing beach AMD mapping can be represented by using RGB imagery with a spatial resolution of about 200 pix/m for detecting macroplastics and, in particular, focusing on the largest items. From the point of view of assessing and monitoring potential sources of MP, this approach is not only feasible but also quick, practical, and sustainable.

Design and Integrated Analysis of a Flexible Support Microstructure with a Honeycomb Sandwich for the Optical Window of a Hypersonic Remote Sensor

In order to reduce the influence of the optical window on the image quality of a hypersonic visible light optical remote sensor, we propose a method of adding a double-layer semicircular honeycomb core microstructure with flexible support of a high temperature elastic alloy between a window glass and a frame to reduce the influence of complex thermal stress on the surface accuracy of the optical window. An equivalent model of a semicircular honeycomb structure was established, the elastic parameters of the semicircular honeycomb sandwich microstructure were derived by an analytical method, and a numerical verification and finite element simulation were carried out. The results show that the equivalent model is in good agreement with the detailed model. The optical-mechanical-thermal integrated simulation analysis of the optical window assembly with flexible supporting microstructure proves that the semicircular honeycomb sandwich flexible supporting structure has a positive effect on stress attenuation of the window glass and ensures the wave aberration accuracy of the transmitted optical path difference of the optical window (PV < 0.665 λ, RMS < 0.156 λ, λ = 632.8 nm). Combined with the actual optical system, the optical performance of the window assembly under the flexible support structure is verified. The simulation results show that the spatial frequency of the modulation transfer function (MTF) of the optical system after focusing is not less than 0.58 in the range of 0–63 cycle/mm and the relative decline of MTF is not more than 0.01, which meet the imaging requirements of a remote sensor. The study results show that the proposed metal-based double-layer semicircular honeycomb sandwich flexible support microstructure ensures the imaging quality of the optical window under ultra-high temperature conditions.

Floating marine litter detection algorithms and techniques using optical remote sensing data: A review

Floating Marine Litter (FML) are mainly plastics or synthetic polymers that float on the sea surface after being deliberately discarded or unintentionally lost along beaches, rivers or marine environments. In recent years, much focus has been placed on locating, tracking and removing plastic items in both coastal areas and in the open ocean. The use of high-resolution multispectral satellite images for such purpose is very promising, since satellite images can systematically monitor much larger areas in comparison to the traditional in situ observations. This paper contains a literature review of the published research regarding the optical remote detection of floating marine debris and the proposed associated methodologies. The main aim of this review is to compile all available information on detection methodologies, providing at the same time valuable insights into the different approaches used for floating marine litter monitoring. First, a brief introduction into the theoretical basis of a spaceborne floating marine litter detection system is given. Next, published articles, or relevant research work have been compartmentalised, for analysing the proposed procedures and assisting in a further assessment of their methodological frameworks. Lastly, conclusions and bottlenecks of the existing knowledge on marine litter detection from space are derived. Although the remote detection of floating marine litter is currently limited by inherent restrictions of the available satellite sensors specifications, we highlight how the methodological processing chain can significantly affect the future accuracy of plastic detection from space.

Advancing Floating Macroplastic Detection from Space Using Experimental Hyperspectral Imagery

Airborne and spaceborne remote sensing (RS) collecting hyperspectral imagery provides unprecedented opportunities for the detection and monitoring of floating riverine and marine plastic debris. However, a major challenge in the application of RS techniques is the lack of a fundamental understanding of spectral signatures of water-borne plastic debris. Recent work has emphasised the case for open-access hyperspectral reflectance reference libraries of commonly used polymer items. In this paper, we present and analyse a high-resolution hyperspectral image database of a unique mix of 40 virgin macroplastic items and vegetation. Our double camera setup covered the visible to shortwave infrared (VIS-SWIR) range from 400 to 1700 nm in a darkroom experiment with controlled illumination. The cameras scanned the samples floating in water and captured high-resolution images in 336 spectral bands. Using the resulting reflectance spectra of 1.89 million pixels in linear discriminant analyses (LDA), we determined the importance of each spectral band for discriminating between water and mixed floating debris, and vegetation and plastics. The absorption peaks of plastics (1215 nm, 1410 nm) and vegetation (710 nm, 1450 nm) are associated with high LDA weights. We then compared Sentinel-2 and Worldview-3 satellite bands with these outcomes and identified 12 satellite bands to overlap with important wavelengths for discrimination between the classes. Lastly, the Normalised Vegetation Difference Index (NDVI) and Floating Debris Index (FDI) were calculated to determine why they work, and how they could potentially be improved. These findings could be used to enhance existing efforts in monitoring macroplastic pollution, as well as form a baseline for the design of future multispectral RS systems.