Characterization of microplastic litter from oceans by an innovative approach based on hyperspectral imaging

Serranti, Silvia; Palmieri, Roberta; Bonifazi, Giuseppe; Cózar, Andrés

doi:10.1016/j.wasman.2018.03.003

Cited by 156 publications

(90 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent innovative approach addresses the characterization of microplastic litter from oceans by hyperspectral imaging [35]. Floating microplastic particles are collected by surface trawling nets for plankton, and then identified in three classes, namely polyethylene (PE), polypropylene (PP), and polystyrene (PS), using morphological and morphometric features.…”

Section: Related Workmentioning

confidence: 99%

SMACC: A System for Microplastics Automatic Counting and Classification

et al. 2020

View full text Add to dashboard Cite

The management of plastic debris is a serious issue due to its durability. Unfortunately, million tons of plastic end up in the sea becoming one of the biggest current environmental problems. One way to monitor the amount of plastic in beaches is to collect samples and visually count and sort the plastic particles present in them. This is a very time-consuming task. In this work, we present a Computer Vision-based system which is able to automatically count and classify microplastic particles (1-5 mm) into five different visual classes. After cleaning a collected sample in the lab, the proposed system makes use of a pair of its images with different characteristics. The procedure includes a segmentation step, which is based on the Sauvola thresholding method, followed by a feature extraction and classification step. Different features and classifiers are evaluated as well as a deep learning approach. The system is tested on 12 different beach samples with a total of 2507 microplastic particles. The particles of each sample were manually counted and sorted by an expert. This data represents the ground truth, which is compared later with the results of the automatic processing proposals to evaluate their accuracy. The difference in the number of particles is 34 (1.4%) and the error in their classification is less than 4% for all types except for the line shapes particles. These results are obtained in less than half of the time needed by the human expert doing the same task manually. This implies that it is possible to process more than twice as many samples using the same time, allowing the biologists to monitor wider areas and more frequently than doing the process manually. INDEX TERMS Computer vision, deep learning, microplastics classification.

show abstract

Section: Related Workmentioning

confidence: 99%

SMACC: A System for Microplastics Automatic Counting and Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Figure 13 shows different pathways of incident light after interacting with the surface (with and without marine plastic). Some studies have used hyperspectral remote sensing to study marine macroplastics [87] and microplastics [88]. Goddijn-Murphy et al [87] considered the spectral signatures and geometric optics of plastic and seawater to develop a reflectance model for detecting macroplastics.…”

Section: Marine Plastic and Coastal Littermentioning

confidence: 99%

Detection and Monitoring of Marine Pollution Using Remote Sensing Technologies

Hafeez¹,

Wong²,

Abbas³

et al. 2019

Monitoring of Marine Pollution

View full text Add to dashboard Cite

Recently, the marine habitat has been under pollution threat, which impacts many human activities as well as human life. Increasing concerns about pollution levels in the oceans and coastal regions have led to multiple approaches for measuring and mitigating marine pollution, in order to achieve sustainable marine water quality. Satellite remote sensing, covering large and remote areas, is considered useful for detecting and monitoring marine pollution. Recent developments in sensor technologies have transformed remote sensing into an effective means of monitoring marine areas. Different remote sensing platforms and sensors have their own capabilities for mapping and monitoring water pollution of different types, characteristics, and concentrations. This chapter will discuss and elaborate the merits and limitations of these remote sensing techniques for mapping oil pollutants, suspended solid concentrations, algal blooms, and floating plastic waste in marine waters.

show abstract

“…The detection of plastics can be improved using cameras extended beyond the visible band 37,[45][46][47][48] . Recently, several researchers have studied the application of near-infrared hyperspectral cameras to identify plastics in the environment [45][46][47][48] . If hyperspectral imaging is available in rivers, macro-plastics can be distinguished from the macro-debris flowing on the river surface.…”

Section: Discussionmentioning

confidence: 99%

Quantification of floating riverine macro-debris transport using an image processing approach

Kataoka

Nihei

2020

Sci Rep

View full text Add to dashboard Cite

A new algorithm has been developed to quantify floating macro-debris transport on river surfaces that consists of three fundamental techniques: (1) generating a difference image of the colour difference between the debris and surrounding water in the CIELuv colour space, (2) detecting the debris pixels from the difference image, and (3) calculating the debris area flux via the template matching method. Debris pixels were accurately detected from the images taken of the laboratory channel and river water surfaces and were consistent with those detected by visual observation. The area fluxes were statistically significantly correlated with the mass fluxes measured through debris collection. The mass fluxes calculated by multiplying the area fluxes with the debris mass per unit area (M/A) were significantly related to the flood rising stage flow rates and agreed with the mass fluxes measured through debris collection. In our algorithm, plastic mass fluxes can be estimated via calibration using the mass percentage of plastics to the total debris in target rivers. Quantifying riverine macro-plastic transport is essential to formulating countermeasures, mitigating adverse plastic pollution impacts and understanding global-scale riverine macro-plastic transport. Quantifying the transport of macro-debris floating on the world's rivers, which are major sources of ocean debris, is essential in formulating countermeasures to mitigate the adverse impacts of land-based loads. In particular, the adverse impacts on aquatic ecosystems of plastics containing toxic chemicals (e.g., persistent organic pollutants (POPs)) 1-4 are recognized as a serious concern in the global aquatic environment 5-8. Many of the plastics in the oceans originate from land 9 , and thereafter, macro-plastics (>25 mm in diameter) 10 are evenly broken down into smaller plastic fragments known as meso-(5−25 mm in diameter) and micro-plastics (<5 mm in diameter) 10 due to photo-and thermo-oxidative degradation 6. Micro-plastics are rarely removed from the aquatic environment when released and are thus gradually transported far away due to ocean currents. Hence, to formulate countermeasures against oceanic plastic pollution, the macro-plastics in rivers must be efficiently captured before being fragmented into smaller pieces and/or being released to the oceans. In particular, because most macro-plastics float on the surface, it is important to understand how floating macro-debris is transported via rivers and then released into the oceans. Recently, a few studies have attempted to estimate the plastic waste emissions from land 9,11. Jambeck et al. 9 , for instance, estimated that 4.8 to 12.7 million tonnes of mismanaged plastic waste could be entering the oceans from 192 coastal countries in 2010 by considering the waste management level in each country and the coastal population. In their estimate, 0.02 to 0.06 million MT of plastic waste can enter the Pacific Ocean from Japan. Moreover, Lebreton et al. 11 estimated that between 1.15 and 2.41 million tonnes ...

show abstract

Characterization of microplastic litter from oceans by an innovative approach based on hyperspectral imaging

Cited by 156 publications

References 36 publications

SMACC: A System for Microplastics Automatic Counting and Classification

SMACC: A System for Microplastics Automatic Counting and Classification

Detection and Monitoring of Marine Pollution Using Remote Sensing Technologies

Quantification of floating riverine macro-debris transport using an image processing approach

Contact Info

Product

Resources

About