|
|
|
Registros recuperados: 44 | |
|
|
Lefort, Riwal; Fablet, Ronan; Boucher, I-m. |
This paper addresses the inference of probabilistic classification models using weakly supervised learning The main contribution of this work is the development of learning methods for training datasets consisting of groups of objects with known relative class priors This can be regarded as a generalization of the situation addressed by Bishop and Ulusoy (2005) where training information is given as the presence or absence of object classes in each set Generative and discriminative classification methods are conceived and compared for weakly supervised learning as well as a non-linear version of the probabilistic discriminative models The considered models are evaluated on standard datasets and an application to fisheries acoustics is reported The proposed... |
Tipo: Text |
Palavras-chave: Weakly supervised learning; Generative classification model; Discriminative classification model. |
Ano: 2011 |
URL: http://archimer.ifremer.fr/doc/00030/14103/11372.pdf |
| |
|
|
Trenkel, Verena; Berger, Laurent; Bourguignon, Sebastien; Doray, Mathieu; Fablet, Ronan; Masse, Jacques; Mazauric, Valerie; Poncelet, Cyrille; Quemener, Gael; Scalabrin, Carla; Villalobos, Hector. |
This paper provides an overview of the progress Ifremer has made recently in fisheries acoustics and the study of small pelagic fish by: i) pushing observation frontiers using a range of platforms including an autonomous underwater vehicle, AUV, ii) developing measuring instruments and methods and iii) studying fish distributions. Presently, information from several frequencies of single-beam echosounders is routinely collected together with data from the ME70 multibeam echosounder. For onboard data acquisition control the HERMES software was developed. The new MOVIES 3D software includes modules for simultaneous realistic 3D visualisation and post-processing such as bottom detection, school extraction and calculation of descriptors and integration of all... |
Tipo: Text |
Palavras-chave: Multibeam echosounder; Oceanographic AUV; Pelagic fish; Fisheries acoustics. |
Ano: 2009 |
URL: http://archimer.ifremer.fr/doc/00000/11165/7517.pdf |
| |
|
|
Heerah, Karine; Woillez, Mathieu; Fablet, Ronan; Garren, Francois; Martin, Stephane; De Pontual, Helene. |
Background Movement pattern variations are reflective of behavioural switches, likely associated with different life history traits in response to the animals’ abiotic and biotic environment. Detecting these can provide rich information on the underlying processes driving animal movement patterns. However, extracting these signals from movement time series, requires tools that objectively extract, describe and quantify these behaviours. The inference of behavioural modes from movement patterns has been mainly addressed through hidden Markov models. Until now, the metrics implemented in these models did not allow to characterize cyclic patterns directly from the raw time series. To address these challenges, we developed an approach to i) extract new metrics... |
Tipo: Text |
Palavras-chave: Fourier transform; Non negative matrix factorization; Classification; Animal behaviour; European sea bass; Movement ecology; Diurnal and tidal cycles; Biologging; Data storage tags. |
Ano: 2017 |
URL: https://archimer.ifremer.fr/doc/00402/51400/51974.pdf |
| |
|
|
De Pontual, Helene; Lalire, Maxime; Fablet, Ronan; Laspougeas, Claire; Garren, Francois; Martin, Stephane; Drogou, Mickael; Woillez, Mathieu. |
From 2010 to 2012, 246 data storage tags were deployed on European seabass in the Iroise Natural Marine Park, a marine protected area (MPA) off west Brittany, France. A return rate of 14.6% associated with long time series of data provided new information on fish ecology (e.g. maximum experienced depth greater than 225 m, temperature range 6.80–21.87°C). Depth and temperature series were used to infer individual migration using an innovative hidden Markov model (HMM) especially developed for seabass geolocation. Reconstructed fish tracks revealed that seabass is a partially migratory species, as individuals exhibited either long-distance migrations towards the Bay of Biscay or the Celtic Sea, or residency behaviour in the Iroise Sea. Fidelity to summer... |
Tipo: Text |
Palavras-chave: Cod; Connectivity; Data Storage Tag (DST); Depth; European sea bass; Dicentrarchus labrax; Geolocation; Partial migration; Spawning site fidelity; Temperature; Vertical movement. |
Ano: 2019 |
URL: https://archimer.ifremer.fr/doc/00451/56230/57790.pdf |
| |
|
|
Maze, Guillaume; Mercier, Herle; Fablet, Ronan; Lenca, Philippe; Piolle, Jean-francois. |
Les bases de données marines, alimentées par les satellites et les robots autonomes sous-marins comme les flotteurs du réseau Argo, sont de plus en plus grandes (plusieurs dizaines de gigaoctets et teraoctets) et rapidement évolutives (elles changent d’heure en heure). Cette augmentation spectaculaire de la dimension et de la complexité des données rend difficile leur exploitation avec les outils standards. Or, c’est à partir de l’analyse des données que les chercheurs pourront réaliser de nouvelles découvertes scientifiques sur la dynamique des océans, à grande et petite échelles, et les changements climatiques régionaux et globaux. L'école d’été OBIDAM14 visait à contribuer à lever ces verrous d’analyse en introduisant les méthodes de fouille de données... |
Tipo: Text |
|
Ano: 2014 |
URL: http://archimer.ifremer.fr/doc/00216/32710/31075.pdf |
| |
|
| |
|
|
Martinez, Elodie; Brini, Anouar; Gorgues, Thomas; Drumetz, Lucas; Roussillon, Joana; Tandeo, Pierre; Maze, Guillaume; Fablet, Ronan. |
Phytoplankton plays a key role in the carbon cycle and supports the oceanic food web. While its seasonal and interannual cycles are rather well characterized owing to the modern satellite ocean color era, its longer time variability remains largely unknown due to the short time-period covered by observations on a global scale. With the aim of reconstructing this longer-term phytoplankton variability, a support vector regression (SVR) approach was recently considered to derive surface Chlorophyll-a concentration (Chl, a proxy of phytoplankton biomass) from physical oceanic model outputs and atmospheric reanalysis. However, those early efforts relied on one particular algorithm, putting aside the question of whether different algorithms may have specific... |
Tipo: Text |
Palavras-chave: Phytoplankton time-series reconstruction; Ocean color; Neural networks; Support vector regression; Multi-layer perceptron; Physical predictors. |
Ano: 2020 |
URL: https://archimer.ifremer.fr/doc/00667/77871/80017.pdf |
| |
|
|
Fablet, Ronan; Pecquerie, Laure; De Pontual, Helene; Hoie, Hans; Millner, Richard; Mosegaard, Henrik; Kooijman, Sebastiaan A. L. M.. |
Otoliths are biocalcified bodies connected to the sensory system in the inner ears of fish. Their layered, biorhythm-following formation provides individual records of the age, the individual history and the natural environment of extinct and living fish species. Such data are critical for ecosystem and fisheries monitoring. They however often lack validation and the poor understanding of biomineralization mechanisms has led to striking examples of misinterpretations and subsequent erroneous conclusions in fish ecology and fisheries management. Here we develop and validate a numerical model of otolith biomineralization. Based on a general bioenergetic theory, it disentangles the complex interplay between metabolic and temperature effects on... |
Tipo: Text |
|
Ano: 2011 |
URL: http://archimer.ifremer.fr/doc/00056/16695/14163.pdf |
| |
|
|
Chessel, Anatole; Fablet, Ronan; Cao, Frederic. |
Otolith are small stone growing according to an accretionary process located in fishes inner ears from which a lot can be learnt about their biology and ecology. Computer vision is one of the mean of systematic analysis of those stone. This paper describe an approach using partial differential equation and variational methods to reconstruct the morphogenesis of an otolith from an image.
|
Tipo: Text |
|
Ano: 2008 |
URL: https://archimer.ifremer.fr/doc/00479/59096/61734.pdf |
| |
|
|
Lefort, Riwal; Fablet, Ronan; Boucher, Jean-marc. |
This chapter deals with object recognition in images involving a weakly supervised classification model. In weakly supervised learning, the label information of the training dataset is provided as a prior knowledge for each class. This prior knowledge is coming from a global proportion annotation of images. In this chapter, we compare three opposed classification models in a weakly supervised classification issue: a generative model, a discriminative model and a model based on random forests. Models are first introduced and discussed, and an application to fishenes acoustics is presented. Experiments show that random forests outperform discriminative and generative models in supervised learning but random forests are not robust to high complexity class... |
Tipo: Text |
|
Ano: 2011 |
URL: http://archimer.ifremer.fr/doc/00077/18782/16489.pdf |
| |
|
| |
|
|
Chessel, Anatole; Cao, F; Fablet, Ronan. |
We develop an axiomatic approach of vector field interpolation, which is useful as a feature extraction preprocessing step. Two operators will be singled out: the curvature operator, appearing in the total variation minimisation for image restoration and inpainting/disocclusion, and the Absolutely Minimizing Lipschitz Extension (AMLE), already known as a robust and coherent scalar image interpolation technique if we relax slightly the axioms. Numerical results, using a multiresolution scheme, show that they produce fields in accordance with the human perception of edges. |
Tipo: Text |
|
Ano: 2006 |
URL: http://archimer.ifremer.fr/doc/00065/17647/15182.pdf |
| |
|
|
Fablet, Ronan; Bouthemy, P. |
A new approach for motion characterization in image sequences is presented. It relies on the probabilistic modeling of temporal and scale co-occurrence distributions of local motion-related measurements directly computed over image sequences. Temporal multiscale Gibbs models allow us to handle both spatial and temporal aspects of image motion content within a unified statistical framework. Since this modeling mainly involves the scalar product between co-occurrence values and Gibbs potentials, we can formulate and address several fundamental issues: model estimation according to the ML criterion (hence, model training and learning) and motion classification. We have conducted motion recognition experiments over a large set of real image sequences... |
Tipo: Text |
Palavras-chave: Nonparametric motion analysis; Motion recognition; Multiscale analysis; Gibbs models; Co occurrences; ML criterion. |
Ano: 2003 |
URL: http://archimer.ifremer.fr/doc/00000/10714/9323.pdf |
| |
|
|
Bourguignon, Sebastien; Berger, Laurent; Scalabrin, Carla; Fablet, Ronan; Mazauric, Valerie. |
Multibeam echosounders and sonars are increasingly used in fisheries acoustics for abundance estimation. Because of reduced side-lobe levels in the beam-array pattern, the new Simrad ME70 multibeam echosounder installed on board Ifremer's RV "Thalassa" has been designed to allow improved detection of fish close to the seabed. To achieve this objective, precise and unambiguous detection of the water-bottom interface is required, which raises the issue of bottom detection, especially in the outer beams. The bottom-detection method implemented in the ME70 is based on the amplitude of the reverberated echo. Such an approach is efficient for vertical beams, but less accurate for beams with higher incidence angles, typically 30°40° for the beam configurations... |
Tipo: Text |
Palavras-chave: Multibeam echosounder; Fisheries; Bottom detection; Acoustics. |
Ano: 2009 |
URL: http://archimer.ifremer.fr/doc/2009/publication-6629.pdf |
| |
|
| |
|
| |
|
|
Bertrand, Sophie; Joo, Rocio; Fablet, Ronan. |
How organisms move and disperse is crucial to understand how population dynamics relates to the spatial heterogeneity of the environment. Random walk (RW) models are typical tools to describe movement patterns. Whether Levy or alternative RW better describes forager movements is keenly debated. We get around this issue using the Generalized Pareto Distribution (GPD). GPD includes as specific cases Normal, exponential and power law distributions, which underlie Brownian, Poisson-like and Levy walks respectively. Whereas previous studies typically confronted a limited set of candidate models, GPD lets the most likely RW model emerge from the data. We illustrate the wide applicability of the method using GPS-tracked seabird foraging movements and fishing... |
Tipo: Text |
|
Ano: 2015 |
URL: https://archimer.ifremer.fr/doc/00275/38641/37160.pdf |
| |
|
|
Pecquerie, Laure; Fablet, Ronan; De Pontual, Helene; Bonhommeau, Sylvain; Alunno-bruscia, Marianne; Petitgas, Pierre; Kooijman, Sebastiaan A. L. M.. |
Environmental conditions experienced by aquatic organisms are archived in biogenic carbonates such as fish otoliths, bivalve shells and coral skeletons. These calcified structures present an accretionary growth and variations in optical properties - color or opacity - that are used to reconstruct time. Full and reliable exploitation of the information extracted from these structures is, however, often limited as the metabolic processes that control their growth and their optical properties are poorly understood. Here, we propose a new modeling framework that couples both the growth of a biogenic carbonate and its optical properties with the metabolism of the organism. The model relies on well-tested properties of Dynamic Energy Budget (DEB) theory. It is... |
Tipo: Text |
Palavras-chave: Otolith; Calcification; Metabolism; Bioenergetic model; Food reconstruction; Dynamic Energy Budget theory. |
Ano: 2012 |
URL: http://archimer.ifremer.fr/doc/00060/17082/14593.pdf |
| |
|
| |
|
|
Fablet, Ronan; Viet, P.; Lguensat, R.; Chapron, Bertrand. |
We address in this paper the reconstruction of irregurlarlysampled image time series with an emphasis on geophysical remote sensing data. We develop a data-driven approach, referred to as an analog assimilation and stated as an ensemble Kalman method. Contrary to model-driven assimilation models, we do not exploit a physically-derived dynamic prior but we build a data-driven dynamic prior from a representative dataset of the considered image dynamics. Our contribution is here to extend analog assimilation to images, which involve high-dimensional state space.We combine patch-based representations to a multiscale PCA-constrained decomposition. Numerical experiments for the interpolation of missing data in satellite-derived ocean remote sensing images... |
Tipo: Text |
Palavras-chave: Data assimilation; Irregular sampling; Image time series; Data-driven methods; Kalman methods. |
Ano: 2017 |
URL: https://archimer.ifremer.fr/doc/00403/51440/52009.pdf |
| |
Registros recuperados: 44 | |
|
|
|