The dataset developed within the PlasticObs+ project aims to facilitate a multi-resolution approach for detecting and quantifying anthropogenic litter through areal images. Traditional detection methods often suffer from narrow, use-case-specific limitations, reducing their transferability. To address this, an image dataset was created featuring various spatial and spectral resolutions. The highest spatial resolution images (ground sampling distance = 0.2 cm) were used to generate a labeled dataset, which was georeferenced for mapping onto coarser-resolution images.
This article introduces an intelligent sensor system installed on a mowing boat operating on the Masch Lake in Hanover, Germany, designed to control unwanted aquatic vegetation. The system adaptively regulates data acquisition based on real-time aquatic plant density estimation and integrates image streams from visible and near-infrared channels, along with 3D point cloud data. A lightweight neural network processes the data on an edge computing platform. By dynamically adjusting the data acquisition rate across four defined mowing stages, the system maximises the relevance of the collected information for subsequent data processing and analysis while minimising the acquisition and storage of irrelevant or redundant data. Field evaluations confirm that the system effectively captures relevant data during ecologically significant stages and suppresses acquisition during less relevant stages, resulting in a dataset of higher informational value. These findings highlight the system’s potential to improve ecological monitoring and enhance operational efficiency in aquatic vegetation management.