UAVs for Fine-Scale Open-Source Landfill Mapping

Abstract

Landfill managers are subject to obligations which include the regular monitoring of the topographical and land cover (LC) evolution of the site. This research aims at developing a cost-effective non-intrusive methodology for mapping landfill LC features. To this end, a state-of-the-art OBIA open-source workflow based on an integration of GRASS GIS and Python programming environment was adapted and applied to 3-cm optical UAV image acquired over the landfill site of Hallembaye (Belgium). The results of this 8class supervised classification are promising with an overall accuracy of 80.5%. This study shows that existing opensource processing chain can be adapted to UAV imagery. In addition, the added value of feature selection and of textural information provided by very high-resolution optical data is also highlighted. Finally, this study illustrates the potential of machine learning for the monitoring of landfill sites.

Методи Машинного Навчання Для Моніторингу Навколишнього Середовища

“…Процес картографування сміттєзвалищ, що здійснюється за допомогою машинного навчання з використанням зображень безпілотного літального апарату (БПЛА), наведено у роботі [5]. Після обробки даних будуються 3D-моделі та визначаються особливості рельєфу.…”

UAV-Based Landfill Land Cover Mapping: Optimizing Data Acquisition and Open-Source Processing Protocols

“…The authors noted that machine learning (ML) and waste recognition algorithms are improving at a rapid pace [13], with new promising application from deep learning (DL) algorithms [14,15]. The review listed only one paper applying ML specifically to landfills for LC features extraction [16], but noted that the technological evolution of these techniques should lead to more publications in the near future.…”

“…OBIA approaches have the advantages of considering shape and texture properties in addition to spectral properties. Wyard et al [16] successfully transposed the OBIA processing chain developed by Grippa et al [22] to UAV data for the automatic LC classification of the Hallembaye landfill site (Wallonia, Belgium) reaching an overall accuracy (OA) of 80.5%. This open-source processing chain includes tools for unsupervised segmentation, its optimization, and multiple ML classification algorithms.…”

“…Beaumont et al [24] and Bassine et al [25] applied it to the classification of aerial orthophotos combined with normalized digital surface models (nDSMs). To our knowledge, this processing chain has only been applied twice to UAV data in addition to the work of Wyard et al [16]. Wijesingha et al [26] performed a binary classification of the invasive plant species Lupinus polyphyllus within grasslands from a red-green-blue (RGB) camera; Souffer et al [27] classified visible and thermal UAV imagery for the automatic extraction of photovoltaic panels, obtaining an F-factor of 98.7%.…”

Supporting Long-Term Archaeological Research in Southern Romania Chalcolithic Sites Using Multi-Platform UAV Mapping

“…The flexibility of image-based modelling platforms, tools, and techniques enables the creation of high-quality 3D reconstructions of a various relics and artifacts. The availability of UASs suitable for photogrammetric applications has increased significantly over the past decades, and the technique is well established for topographic mapping and archaeological documentation [9,10].…”