Rinze de Vries

Tudelft, Sepam, Graduate Student

Followers

Following

Public Views

I am a person who is never afraid of rolling up my sleeves and start working on new projects. Always interested in new challenges, and often eagerly in the search for new and better solutions for known problems. This results in some characteristics like: Social, Driven, Independent and DisciplinedSome special areas of interests are: Water management, Durability, Innovation

less

Teresa Marat-Mendes

ISCTE - University Institute of Lisbon (ISCTE-IUL)

David Seamon

Kansas State University

Murat Cemal Yalcintan

Msgsu

Catalina Ortiz

University College London

Akhmad Safik

Universitas Al Azhar Indonesia

Johannes Preiser-Kapeller

Austrian Academy of Sciences

Patrick Simon

Institut National d'Etudes Démographiques

Uday Chandra

SFS Qatar (Georgetown University)

Ringo W Tenga

University of Dar es Salaam

Abigail A Sewell

Emory University

Interests

Uploads

Papers by Rinze de Vries

Detecting Floating Macroplastic Litter with Semi-Supervised Deep Learning

Advancing deep learning-based detection of floating litter using a novel open dataset

Frontiers in water, Dec 5, 2023

Supervised Deep Learning (DL) methods have shown promise in monitoring the floating litter in riv... more Supervised Deep Learning (DL) methods have shown promise in monitoring the floating litter in rivers and urban canals but further advancements are hard to obtain due to the limited availability of relevant labeled data. To address this challenge, researchers often utilize techniques such as transfer learning (TL) and data augmentation (DA). However, there is no study currently reporting a rigorous evaluation of the e ectiveness of these approaches for floating litter detection and their e ects on the models' generalization capability. To overcome the problem of limited data availability, this work introduces the "TU Delft-Green Village" dataset, a novel labeled dataset of , camera and phone images of floating macroplastic litter and other litter items, captured using experiments in a drainage canal of TU Delft. We use the new dataset to conduct a thorough evaluation of the detection performance of five DL architectures for multi-class image classification. We focus the analysis on a systematic evaluation of the benefits of TL and DA on model performances. Moreover, we evaluate the generalization capability of these models for unseen litter items and new device settings, such as increasing the cameras' height and tilting them to •. The results obtained show that, for the specific problem of floating litter detection, fine-tuning all layers is more e ective than the common approach of fine-tuning the classifier alone. Among the tested DA techniques, we find that simple image flipping boosts model accuracy the most, while other methods have little impact on the performance. The SqueezeNet and DenseNet architectures perform the best, achieving an overall accuracy of. and. %, respectively. We also observe that both models retain good generalization capability which drops significantly only for the most complex scenario tested, but the overall accuracy raises significantly to around % when adding a limited amount of images to training data, combined with flipping augmentation. The detailed analyses conducted here and the released open source dataset o er valuable insights and serve as a precious resource for future research.

Download

TUD-GV Dataset for Floating Litter Detection

Zenodo (CERN European Organization for Nuclear Research), Apr 19, 2023

Deep learning for detecting macroplastic litter in water bodies: A review

Water Research, Mar 1, 2023

Plastic pollution in water bodies is an unresolved environmental issue that damages all aquatic e... more Plastic pollution in water bodies is an unresolved environmental issue that damages all aquatic environments, and causes economic and health problems. Accurate detection of macroplastic litter (plastic items >5 mm) in water is essential to estimate the quantities, compositions and sources, identify emerging trends, and design preventive measures or mitigation strategies. In recent years, researchers have demonstrated the potential of computer vision (CV) techniques based on deep learning (DL) for automated detection of macroplastic litter in water bodies. However, a systematic review to describe the state-of-the-art of the field is lacking. Here we provide such a review, and we highlight current knowledge gaps and suggest promising future research directions. The review compares 34 papers with respect to their application and modeling related criteria. The results show that the researchers have employed a variety of DL architectures implementing different CV techniques to detect macroplastic litter in various aquatic environments. However, key knowledge gaps must be addressed to overcome the lack of: (i) DL-based macroplastic litter detection models with sufficient generalization capability, (ii) DL-based quantification of macroplastic (mass) fluxes and hotspots and (iii) scalable macroplastic litter monitoring strategies based on robust DL-based quantification. We advocate for the exploration of data-centric artificial intelligence approaches and semi-supervised learning to develop models with improved generalization capabilities. These models can boost the development of new methods for the quantification of macroplastic (mass) fluxes and hotspots, and allow for structural monitoring strategies that leverage robust DL-based quantification. While the identified gaps concern all bodies of water, we recommend increased efforts with respect to riverine ecosystems, considering their major role in transport and storage of litter.

Download

An open source dataset for Deep Learning-based visual detection of floating macroplastic litter

&lt;p&gt;Plastic pollution of water bodies is a major environmental issue, as it can have... more &lt;p&gt;Plastic pollution of water bodies is a major environmental issue, as it can have harmful effects on marine life, riverine ecosystems and society as a whole. To mitigate the impacts of plastic pollution, accurate detection and quantification of macroplastic litter (plastic items &gt; 5 mm) is of particular importance. In recent years, researchers and engineers have developed Deep Learning methods showing promising performances for detecting riverine macroplastic litter. However, there are several outstanding issues hindering the advancement of the field, including the lack of available data sources for training such models.&lt;/p&gt; &lt;p&gt;Here, we present a new open source dataset for the detection of floating macroplastic litter. We generated the dataset from controlled experiments carried out in a small drainage canal on the TU Delft campus. The dataset features 626 different litter items including plastic bottles, bags and other plastic objects, as well as metal tins and paper litter. These items include household waste as well as litter recovered from canals in the Netherlands. We captured images with a resolution of 1080p and a linear field of view using two different action cameras and a phone, mounted on a bridge. The dataset consists of 10000 images, taken from two different heights (2.7 and 4.0 meters), two different inclinations (0 and 45 degrees from the horizontal), and two different weather conditions (sunny and cloudy sky).&lt;/p&gt; &lt;p&gt;In this presentation, we provide information on the dataset and the experiments carried out to generate it. We also discuss the results of benchmark Deep Learning models for multi-class classification trained on the dataset, and their out-of-sample generalization ability to other case studies. While labels are currently available only for image classification, we aim to release annotations for object detection and image segmentation tasks in the future.&lt;/p&gt;

Programme of requirements for the design of an instrument that assists spatial planners in assessing flood risk: A research towards the questions if- and how- an instrument that presents information to users form a different dsicipline that the designers can be improved

An open source dataset for Deep Learning-based visual detection of floating macroplastic litter

Deep learning for detecting macroplastic litter in water bodies: A review

Water Research

Flood risk is increasing due to climate change and the growth of the potential consequences of fl... more Flood risk is increasing due to climate change and the growth of the potential consequences of flooding. Analysing how flood-proof the spatial plan is, therefore becomes more important. Since most spatial planners have limited knowledge concerning flood risk, the Netherlands’ Directorate-General for Public Works and Water Management commissioned the creation of an instrument that can be used by planners to gain a better insight into the flood risk. However, this instrument is used inadequately. This research focuses on the question: What are design requirements for an instrument that helps to assess flood risk during spatial planning processes? And, what does this set of requirements mean for the design and use of the current MLS Explorer?This resulted in the findings that lead to a programme of requirements, the main findings were:(1) The best moment to use the Explorer is early in the spatial planning process; (2) The Explorer is most interesting for local government organisations...

A robust deep learning methodology to detect floating macro-plastic litter in rivers

&amp;lt;p&amp;gt;Plastic pollution in rivers is a serious environmental concern. To impro... more &amp;lt;p&amp;gt;Plastic pollution in rivers is a serious environmental concern. To improve the monitoring of floating macro-plastic litter in water, researchers increasingly resort to automatic detection tools based on Artificial Intelligence (AI) for Computer Vision (CV). The most advanced applications feature Deep Learning (DL) methods based on Convolutional Neural Networks (CNN) achieving state-of-the-art performances in standard CV datasets (e.g., ImageNet).&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;Despite promising initial results, only few studies validated the generalization ability of DL models across different locations, environmental conditions, and instrumental setups. Poor generalization results in the need for a new model for each different setting. This increases the data requirements and limits the applicability. These aspects are essential for practical implementations such as the development of a structural monitoring strategy backed by a reliable AI model.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;In this work, we discuss how to develop a robust DL methodology by harnessing recent advancements in AI, such as data-centric AI and semi-supervised learning. We also show the effects of implementing these techniques on the generalization performances of a DL model by employing two different datasets of floating macro-plastic in rivers. The first is a new dataset recorded in a semi-controlled environment featuring a small drainage canal in the Netherlands; the second is a dataset available from the literature, with images from different waterways in Jakarta, Indonesia. The significant diversity among the two datasets grants a sound evaluation of model generalization performances and on the suitability of the proposed methodology for achieving increased robustness.&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;&amp;lt;/p&amp;gt;&amp;lt;p&amp;gt;&amp;lt;/p&amp;gt;

Detecting Floating Macroplastic Litter with Semi-Supervised Deep Learning

Advancing deep learning-based detection of floating litter using a novel open dataset

Frontiers in water, Dec 5, 2023

Download

TUD-GV Dataset for Floating Litter Detection

Zenodo (CERN European Organization for Nuclear Research), Apr 19, 2023

Deep learning for detecting macroplastic litter in water bodies: A review

Water Research, Mar 1, 2023

Download

An open source dataset for Deep Learning-based visual detection of floating macroplastic litter

Deep learning for detecting macroplastic litter in water bodies: A review

Water Research

A robust deep learning methodology to detect floating macro-plastic litter in rivers

Rinze de Vries

Uploads

Papers by Rinze de Vries

Log In