Search results for "CLASSIFICATION."

Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks

2020

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were emp…

Changements environnementaux survenant à la limite Oligocène/Miocène du bassin des Limagnes (Massif central, France).

2018

16 pages; International audience; Continental environments are very sensitive to climatic variations. A unique opportunity to study the climate changes around the Oligocene/Miocene boundary is offered by the Limagne graben Basin (France) where this stage boundary is well constrained by fossils. Indeed, some localities of the Limagne Graben Basin are so rich in mammal remains that they have become a European reference for mammal biostratigraphy. The dominant sedimentary facies of the lacustrine deposits in the northern part of the Limagne Graben Basin are composed of poorly cemented marls and calcarenites containing various plants and animals remains (e.g. algae, fish bones and teeth, gastro…

Efficient remote sensing image classification with Gaussian processes and Fourier features

2017

This paper presents an efficient methodology for approximating kernel functions in Gaussian process classification (GPC). Two models are introduced. We first include the standard random Fourier features (RFF) approximation into GPC, which largely improves the computational efficiency and permits large scale remote sensing data classification. In addition, we develop a novel approach which avoids randomly sampling a number of Fourier frequencies, and alternatively learns the optimal ones using a variational Bayes approach. The performance of the proposed methods is illustrated in complex problems of cloud detection from multispectral imagery.

SVM-based classification of High resolution Urban Satellites Images using Dense SURF and Spectral Information

2018

Remote-sensing focusing on image classification knows a large progress and receives the attention of the remote-sensing community day by day. Combining many kinds of extracted features has been successfully applied to High resolution urban satellite images using support vector machine (SVM). In this paper, we present a methodology that is promoting a performed classification by using pixel-wise SURF description features combined with spectral information in Cielab space for the first time on common scenes of urban imagery. The proposed method gives a promising classification accuracy when compared with the two types of features used separately.

SAR Image Classification Combining Structural and Statistical Methods

2011

The main objective of this paper is to develop a new technique of SAR image classification. This technique combines structural parameters, including the Sill, the slope, the fractal dimension and the range, with statistical methods in a supervised image classification. Thanks to the range parameter, we define the suitable size of the image window used in the proposed approach of supervised image classification. This approach is based on a new way of characterising different classes identified on the image. The first step consists in determining relevant area of interest. The second step consists in characterising each area identified, by a matrix. The last step consists in automating the pr…

Relations between Air Quality and Covid-19 Lockdown Measures in Valencia, Spain

2021

The set of measures to contain the diffusion of COVID-19 instituted by the European governments gave an unparalleled opportunity to improve our understanding of the transport and industrial sectors’ contribution to urban air pollution. The purpose of this study was to assess the impacts of the lockdown measures on air quality and pollutant emissions in Valencia, Spain. For this reason, we determined if there was a significant difference in the concentration levels of different particulate matter (PM) sizes, PM10, PM2.5, and NOx, NO2, NO, and O3, between the period of restrictions in 2020 and the same period in 2019. Our findings indicated that PM pollutant levels during the lockdown period…

Environmental change during the Early Cretaceous in the Purbeck-type Durlston Bay section (Dorset, Southern England): a biomarker approach.

2007

20 pages; International audience; The Purbeck-type section (Durlston Bay, Dorset, UK) exhibits littoral lagoonal to lacustrine facies. It shows a gradual climatic/environmental change from semi-arid conditions associated with evaporites at the Jurassic–Cretaceous transition, to a more humid climate at the end of the Berriasian. Though generally organic-poor (total organic carbon, TOC, <1.3%), the Durlston Bay section shows an organic-rich episode (TOC up to 8.5%) located at the transition from evaporitic to more humid facies. A biomarker study was performed in order to determine the origin of the organic matter (OM) in the section and see if changes in organic sources accompanied the genera…

Understanding deep learning in land use classification based on Sentinel-2 time series

2020

AbstractThe use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims …

Two decades of monitoring in marine debris ingestion in loggerhead sea turtle, Caretta caretta, from the western Mediterranean

2018

Abstract Anthropogenic marine debris is one of the major worldwide threats to marine ecosystems. The EU Marine Strategy Framework Directive (MSFD) has established a protocol for data collection on marine debris from the gut contents of the loggerhead sea turtle (Caretta caretta), and for determining assessment values of plastics for Good Environmental Status (GES). GES values are calculated as percent turtles having more than average plastic weight per turtle. In the present study, we quantify marine debris ingestion in 155 loggerhead sea turtles collected in the period 1995–2016 in waters of western Mediterranean (North-east Spain). The study aims (1) to update and standardize debris inges…

2021

Abstract Contaminated soils are lands in Europe deemed less favourable for conventional agriculture. To overcome the problem of their poor fertility, bio-fertilization could be a promising approach. Soil inoculation with a choice of biological species (e.g. earthworm, mycorrhizal fungi, diazotroph bacteria) can be performed in order to improve soil properties and promote nutrients recycling. However, questions arise concerning the dynamics of the contaminants in an inoculated soil. The aim of this study was to highlight the soil-plant-earthworm interactions in the case of a slightly contaminated soil. For this purpose, a pot experiment in controlled conditions was carried out during 2 month…