Recently, a variety of approaches have been enriching the field of remote sensing (RS) image processing and analysis. Unfortunately, existing methods remain limited to the rich spatiospectral content ...of today's large data sets. It would seem intriguing to resort to deep learning (DL)-based approaches at this stage with regard to their ability to offer accurate semantic interpretation of the data. However, the specificity introduced by the coexistence of spectral and spatial content in the RS data sets widens the scope of the challenges presented to adapt DL methods to these contexts. Therefore, the aim of this paper is first to explore the performance of DL architectures for the RS hyperspectral data set classification and second to introduce a new 3-D DL approach that enables a joint spectral and spatial information process. A set of 3-D schemes is proposed and evaluated. Experimental results based on well-known hyperspectral data sets demonstrate that the proposed method is able to achieve a better classification rate than state-of-the-art methods with lower computational costs.
Este texto procura demostrar cómo Le Corbusier, a través de los viajes de 1929 y 1936 a Río de Janeiro, no solo proporciona las bases de la arquitectura moderna en el país, sino que también ...problematiza la relación entre espacio construido y naturaleza. Frente a una realidad completamente distinta de aquella del Viejo Mundo, puesto que la naturaleza tropical se impone, el arquitecto franco-suizo se ve impulsado a jugar una partida entre afirmación-hombre y presencia-naturaleza. Tanto Lucio Costa como la primera generación de arquitectos modernos cariocas (Oscar Niemeyer, Alfonso Eduardo Reidy, Jorge Moreira, los hermanos Roberto, entre otros) realizan significativos aportes hacia interpretaciones originales que subvierten y amplían las categorías propuestas por Le Corbusier. Tal empeño –que desarrolla medios diversos de una fluidez entre adentro y afuera, edificio y paisaje– tiene al final una repercusión en la propia aprehensión visual del edificio con los elementos icónicos de ese paisaje: la selva tropical, el morro del Pan de azúcar y la Bahía de Guanabara.
In recent years, privacy concerns have become a serious issue for companies wishing to protect economic models and comply with end-user expectations. In the same vein, some countries now impose, by ...law, constraints on data use and protection. Such context thus encourages machine learning to evolve from a centralized data and computation approach to decentralized approaches. Specifically, Federated Learning (FL) has been recently developed as a solution to improve privacy, relying on local data to train local models, which collaborate to update a global model that improves generalization behaviors. However, by definition, no computer system is entirely safe. Security issues, such as data poisoning and adversarial attack, can introduce bias in the model predictions. In addition, it has recently been shown that the reconstruction of private raw data is still possible. This paper presents a comprehensive study concerning various privacy and security issues related to federated learning. Then, we identify the state-of-the-art approaches that aim to counteract these problems. Findings from our study confirm that the current major security threats are poisoning, backdoor, and Generative Adversarial Network (GAN)-based attacks, while inference-based attacks are the most critical to the privacy of FL. Finally, we identify ongoing research directions on the topic. This paper could be used as a reference to promote cybersecurity-related research on designing FL-based solutions for alleviating future challenges.
Ocean surface monitoring, emphasizing oil slick detection, has become essential due to its importance for oil exploration and ecosystem risk prevention. Automation is now mandatory since the manual ...annotation process of oil by photo-interpreters is time-consuming and cannot process the data collected continuously by the available spaceborne sensors. Studies on automatic detection methods mainly focus on Synthetic Aperture Radar (SAR) data exclusively to detect anthropogenic (spills) or natural (seeps) oil slicks, all using limited datasets. The main goal is to maximize the detection of oil slicks of both natures while being robust to other phenomena that generate false alarms, called “lookalikes”. To this end, this paper presents the automation of offshore oil slick detection on an extensive database of real and recent oil slick monitoring scenarios, including both types of slicks. It relies on slick annotations performed by expert photo-interpreters on Sentinel-1 SAR data over four years and three areas worldwide. In addition, contextual data such as wind estimates and infrastructure positions are included in the database as they are relevant data for oil detection. The contributions of this paper are: (i) A comparative study of deep learning approaches using SAR data. A semantic and instance segmentation analysis via FC-DenseNet and Mask R-CNN, respectively. (ii) A proposal for Fuse-FC-DenseNet, an extension of FC-DenseNet that fuses heterogeneous SAR and wind speed data for enhanced oil slick segmentation. (iii) An improved set of evaluation metrics dedicated to the task that considers contextual information. (iv) A visual explanation of deep learning predictions based on the SHapley Additive exPlanation (SHAP) method adapted to semantic segmentation. The proposed approach yields a detection performance of up to 94% of good detection with a false alarm reduction ranging from 14% to 34% compared to mono-modal models. These results provide new solutions to improve the detection of natural and anthropogenic oil slicks by providing tools that allow photo-interpreters to work more efficiently on a wide range of marine surfaces to be monitored worldwide. Such a tool will accelerate the oil slick detection task to keep up with the continuous sensor acquisition. This upstream work will allow us to study its possible integration into an industrial production pipeline. In addition, a prediction explanation is proposed, which can be integrated as a step to identify the appropriate methodology for presenting the predictions to the experts and understanding the obtained predictions and their sensitivity to contextual information. Thus it helps them to optimize their way of working.
Quality Assessment of Stereoscopic Images Benoit, Alexandre; Le Callet, Patrick; Campisi, Patrizio ...
EURASIP journal on image and video processing,
01/2008, Letnik:
2008, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Several metrics have been proposed in literature to assess the perceptual quality of two-dimensional images. However, no similar effort has been devoted to quality assessment of stereoscopic images. ...Therefore, in this paper, we review the different issues related to 3D visualization, and we propose a quality metric for the assessment of stereopairs using the fusion of 2D quality metrics and of the depth information. The proposed metric is evaluated using the SAMVIQ methodology for subjective assessment. Specifically, distortions deriving from coding are taken into account and the quality degradation of the stereopair is estimated by means of subjective tests.
This paper reports on a water flow energy harvester exploiting a horizontal axis turbine with distributed magnets of alternate polarities at the rotor periphery and air coils outside the pipe. The ...energy harvester operates down to 1.2L/min with an inlet section of 20mm of diameter and up to 25.2mW are provided at 20L/min in a 2.4V NiMH battery through a BQ25504 power management circuit. The pressure loss induced by the insertion of the energy harvester in the hydraulic circuit and by the extraction of energy has been limited to 0.05bars at 30L/min, corresponding to a minor loss coefficient of KEH=3.94.
It is well known that the order- n truncation of the Chebyshev expansion of a function over a given interval is a near-best uniform polynomial approximation of the function on that interval. In the ...case of solutions of linear differential equations with polynomial coefficients, the coefficients of the expansions obey linear recurrence relations with polynomial coefficients. Unfortunately, these recurrences do not lend themselves to a direct recursive computation of the coefficients, owing among other things to a lack of initial conditions.
Abstract
Amphibians are ideal for studying visual system evolution because their biphasic (aquatic and terrestrial) life history and ecological diversity expose them to a broad range of visual ...conditions. Here, we evaluate signatures of selection on visual opsin genes across Neotropical anurans and focus on three diurnal clades that are well-known for the concurrence of conspicuous colors and chemical defense (i.e., aposematism): poison frogs (Dendrobatidae), Harlequin toads (Bufonidae: Atelopus), and pumpkin toadlets (Brachycephalidae: Brachycephalus). We found evidence of positive selection on 44 amino acid sites in LWS, SWS1, SWS2, and RH1 opsin genes, of which one in LWS and two in RH1 have been previously identified as spectral tuning sites in other vertebrates. Given that anurans have mostly nocturnal habits, the patterns of selection revealed new sites that might be important in spectral tuning for frogs, potentially for adaptation to diurnal habits and for color-based intraspecific communication. Furthermore, we provide evidence that SWS2, normally expressed in rod cells in frogs and some salamanders, has likely been lost in the ancestor of Dendrobatidae, suggesting that under low-light levels, dendrobatids have inferior wavelength discrimination compared to other frogs. This loss might follow the origin of diurnal activity in dendrobatids and could have implications for their behavior. Our analyses show that assessments of opsin diversification in across taxa could expand our understanding of the role of sensory system evolution in ecological adaptation.
Diffuse large B cell lymphoma (DLBCL) is successfully treated with combination immuno-chemotherapy, but relapse with resistant disease occurs in ~ 40% of patients. However, little is known regarding ...relapsed/refractory DLBCL (rrDLBCL) genetics and alternative therapies. Based on findings from other tumors, we hypothesized that RAS-MEK-ERK signaling would be upregulated in resistant tumors, potentially correlating with mutations in RAS, RAF, or associated proteins. We analyzed mutations and phospho-ERK levels in tumor samples from rrDLBCL patients. Unlike other tumor types, rrDLBCL is not mutated in any Ras or Raf family members, despite having increased expression of p-ERK. In paired biopsies comparing diagnostic and relapsed specimens, 33% of tumors gained p-ERK expression, suggesting a role in promoting survival. We did find mutations in several Ras-associating proteins, including GEFs, GAPs, and downstream effectors that could account for increased ERK activation. We further investigated mutations in one such protein, RASGRP4. In silico modeling indicated an increased interaction between H-Ras and mutant RASGRP4. In cell lines, mutant RASGRP4 increased basal p-ERK expression and lead to a growth advantage in colony forming assays when challenged with doxorubicin. Relapsed/refractory DLBCL is often associated with increased survival signals downstream of ERK, potentially corresponding with mutations in protein controlling RAS/MEK/ERK signaling.