Search

The abundance of beach litter has been increasing globally during the last decades, and it is an issue of global concern. A new survey strategy, based on uncrewed aerial vehicles (UAV, aka drones), has been recently adopted to improve the monitoring of beach macro-litter items abundance and distribution. This work identified and analysed the 15 studies that used drone for beach litter surveys on an operational basis. The analysis of technical parameters for drone flight deployment revealed that flight altitude varied between 5 and 40 m. The analysis of final assessments showed that, through manual and/or automated items detection on images, most of studies provided litter bulk characteristics (type, material and size), along with litter distribution maps. The potential standardization of drone-based litter survey would allow a comparison among surveys, however it seems difficult to propose a standard set of flight parameters, given the wide variety of coastal environments, the different devices available, and the diverse objectives of drone-based litter surveys. On the other hand, in our view, a set of common outcomes can be proposed, based on the grid mapping process, which can be easily generated following the procedure indicated in the paper. This work sets the ground for the development of a standardized protocol for drone litter data collection, analysis and assessments. This would allow the provision of broad scale comparative studies to support coastal management at both national and international scales. [Display omitted] • Revision of the 15 studies that exploited drones for beached litter survey on an operational basis. • Drone flight altitude varied between 5 and 40 m, drone image resolution varied between 0.01 and 1.2 cm/pixels. • Assessments included detailed litter characterization and distribution maps. • A potential homogenization of assessments, based on grid mapping, may support surveys comparison. [ABSTRACT FROM AUTHOR]

The use of Unmanned Aerial Systems (UAS, aka drones) images for mapping macro-litter in the environment have been exponentially increasing in the recent years. In this work, we developed a multi-class Neural Network (NN) to automatically identify stranded plastic litter categories on an UAS-derived orthophoto. The best results were assessed for items that did not have substantial intra-class colour variability, such as octopus pots and fishing ropes (F-score = 61%, on average). Instead, performance was poor (37%) for plastic bottles and fragments, due to their changing intra-class colours. On average, the performance improved 24% when the binary detection (litter/non-litter, F-Score = 73%) was considered, however this approach did not discriminate the litter categories. This work gives a new perspective for the automated litter detection on drone images, suggesting that colour-based approach can be used to improve the categorization of stranded litter on UAS orthophoto. [Display omitted] • Images collected by drone for mapping stranded macro-litter • Multi-class Neural Network for the automated detection • Colour-based approach for identifying different plastic categories • Best performance for items with low intra-class colour variability [ABSTRACT FROM AUTHOR]

• Characterisation of drone images with 9 parameters to reconstruct coastal cliffs. • In-depth analysis of two image networks with 3D image coverage maps. • Diverse image coverage and different level of details of the complex areas. • Identical similarity in respect to the established survey requirements. • Towards an optimised drone acquisition scheme for monitoring coastal cliffs. Drones are cost-efficient tools to survey coastal cliffs. Two different drone flights were performed to reconstruct a coastal cliff face through the Structure from Motion technique.The collected images were characterised by a set of nine parameters, which were related to the image network and the image plane. The 3D image coverage map was proposed for an in-depth analysis of the image network. In terms of accuracy of the 3D reconstruction, positional errors were of 6.5 cm. Between the two flights, the main differences regarded the image redundancy (18) and the image incident angle (33°). These determined a diverse image coverage, and thus a different level of details of the complex cliff face areas. However, both image networks presented an identical similarity (0.34-0.32) in respect to the established survey requirements. This work can support the development of an optimised drone acquisition scheme for the 3D reconstruction of coastal cliffs. [ABSTRACT FROM AUTHOR]