Smart farming is increasingly becoming a significant research topic with the emergence of advanced technologies and artificial intelligence tools. This study focuses on automated dairy cattle monitoring based on deep learning techniques. A pipeline involving multiple cows detection followed by tracking module is considered. In this research, we compare different detection models as well as state-of-the-art trackers. We employ an ablation strategy for the evaluation of the pipeline, by testing separately these models, and finally proposing an end-to-end system that achieves high scores according to known metrics in the field.

In this paper, we are interested in detecting and classifying vocal folds disorders from high speed videos. Our contribution aims to jointly exploit the spatial and temporal information related to the vocal folds, by resorting to various 3 D spatiotemporal architectures. Another novelty consists in evaluating the influence of the region of interest delineation on the multiclassification performances. In our experiments, several types of disorders have been considered on high speed endoscopy videos. Experimental results indicate the gain achieved by capturing the spatio-temporal features.

This paper introduces a novel optimization approach for stain separation in digital histopathological images. Our stain separation cost function incorporates a smooth total variation regularization and is minimized by using a projected gradient algorithm. To enhance computational efficiency and enable supervised learning of the hyperparameters, we further unroll our algorithm into a neural network. The unrolled architecture is not only more efficient for solving the stain separation problem, but also allows to design a highly interpretable and flexible method. Experimental results demonstrate the effectiveness of the proposed unrolled projected gradient algorithm in achieving accurate and visually consistent stain separation.

The optimization of prediction and update operators plays a prominent role in lifting-based image coding schemes. In this paper, we focus on learning the prediction and update models involved in a recent Fully Connected Neural Network (FCNN)-based lifting structure. While a straightforward approach consists in separately learning the different FCNN models by optimizing appropriate loss functions, jointly learning those models is a more challenging problem. To address this problem, we first consider a statistical model-based entropy loss function that yields a good approximation to the coding rate. Then, we develop a multi-scale optimization technique to learn all the FCNN models simultaneously. For this purpose, two loss functions defined across the different resolution levels of the proposed representation are investigated. While the first function combines standard prediction and update loss functions, the second one aims to obtain a good approximation to the rate-distortion criterion. Experimental results carried out on two standard image datasets, show the benefits of the proposed approaches in the context of lossy and lossless compression.

In this paper, we are interested in the design of deep-learning-based computer-aided diagnosis systems that recognize laryngeal diseases. Our contribution consists in studying the impact of exploiting the spatio-temporal information on the classification performance. Experimental results, carried out on vocal fold high speed videos allow to compare the performances of the spatio-temporal deep neural network network with those of a purely spatial deep architecture.

In this work, we propose a fast, accessible and accurate method for classifying image of water samples according to the turbidity. Our contribution consists in designing and implementing an end to end solution that benefits both expert users and common citizens. The contribution relies on several aspects: the construction of an automatically labelled image database via a mobile application connected to an IoT platform, the acquisition procedure and, the machine learning method to derive an accurate classification model of the turbidity.

Lifting-based wavelet transform has been extensively used for efficient compression of various types of visual data. Generally, the performance of such coding schemes strongly depends on the lifting operators used, namely the prediction and update filters. Unlike conventional schemes based on linear filters, we propose, in this paper, to learn these operators by exploiting neural networks. More precisely, a classical Fully Connected Neural Network (FCNN) architecture is firstly employed to perform the prediction and update. Then, we propose to improve this FCNN-based Lifting Scheme (LS) in order to better take into account the input image to be encoded. Thus, a novel dynamical FCNN model is developed, making the learning process adaptive to the input image contents for which two adaptive learning techniques are proposed. While the first one resorts to an iterative algorithm where the computation of two kinds of variables is performed in an alternating manner, the second learning method aims to learn the model parameters directly through a reformulation of the loss function. Experimental results carried out on various test images show the benefits of the proposed approaches in the context of lossy and lossless image compression.

The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an $\ell_{p}$ loss function, with $p\in\{1,2\}$, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted $\ell_{p}$ loss function related to the global prediction error. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.

Wavelet decompositions based on lifting schemes have been widely used in image coding. Generally, the efficiency of such compression methods strongly depends on the design of the lifting operators, namely the prediction and update filters. To improve their performance, we propose in this paper to optimize these filters by resorting to two learning strategies. In the first one, classical Fully Connected Networks (FCNs) are exploited to perform the prediction and update. In the second approach, we develop an adaptive learning method that takes into account the input image, yielding a dynamical model of FCN. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits that can be drawn from the proposed approaches compared to conventional ones.

In this letter, we propose a fast and accurate approximation of the Kullback-Leibler divergence (KLD) between two Bernoulli-Generalized Gaussian (Ber-GG) distributions. Such a distribution has been found to be well suited for modeling sparse signals like wavelet-based representations. On the basis of high-bitrate approximations of the entropy of quantized Ber-GG sources, we provide a close approximation of the KLD without resorting to the conventional time-consuming Monte Carlo estimation approach. The developed approximation formula is then validated in the context of depth map and stereo image retrieval.

In this paper, we address the issue of designing a smoke detector robust to illumination variations. Our contribution consists in resorting to color invariants as salient smoke features. More precisely, the proposed detector employs consecutively of an illumination invariant color representation, a photometric gain based background subtraction, a chrominance detection and a smoke identification based on two invariant color descriptors. The experimental results show that the proposed method can effectively detect smoke with robustness to illumination changes and noises, frequently encountered in wildfire video-surveillance environments.

The great interest of stereo images in several applications has led to the proliferation of huge and ever growing image databases. Therefore, there is an urgent demand for an effective Content Based Image Retrieval (CBIR) system devoted to stereo images. To meet such a demand, this paper proposes new wavelet-based retrieval approaches that exploit not only the visual contents of the Stereo Image (SI) pair but also its related disparity field. The first approach takes into account implicitly the disparity information by computing features from the disparity compensated left image and the right image. The second one aims at extracting relevant features directly from the left and right views, and the disparity map. Experimental results indicate that adding disparity information allows us to improve the retrieval performances of stereo images.

Recent research efforts have been devoted to the improvement of image retrieval systems when datasets are represented in a compressed form. In this context, new studies have shown that compression has a negative impact on the performances of the traditional retrieval systems. In this work, we are mainly interested in designing an efficient retrieval approach well adapted to wavelet-based compressed images. More precisely, we first propose to apply a compression scheme based on the Moment Preserving Quantization (MPQ). Then, the feature vectors will be defined in an appropriate way by focusing on the quantized subbands where some given statistical moments have been preserved. Experimental results indicate that the proposed approach outperforms the most recent one which involves the conventional uniform quantizer and constrains the query and the model images to have similar qualities during the retrieval step.

In multichannel imaging, several observations of the same scene acquired in different spectral ranges are available. Very often, the spectral components are degraded by a blur modelled by a linear operator and an additive noise. In this paper, we address the problem of recovering the image components in a wavelet domain by adopting a variational approach. Our contribution is twofold. First, an appropriate multivariate penalty function is derived from a novel joint prior model of the probability distribution of the wavelet coefficients located at the same spatial position in a given subband through all the channels. Secondly, we address the challenging issue of computing the Maximum A Posteriori estimate by using a Majorize-Minimize optimization strategy. Simulation tests carried out on multispectral satellite images show that the proposed method outperforms conventional techniques.

Many existing works related to lossy-to-lossless image compression are based on the lifting concept. In this paper, we present a sparse optimization technique based on recent convex algorithms and applied to the prediction filters of a two-dimensional non separable lifting structure. The idea consists of designing these filters, at each resolution level, by minimizing the sum of the ℓ1-norm of the three detail subbands. Extending this optimization method in order to perform a global minimization over all resolution levels leads to a new optimization criterion taking into account linear dependencies between the generated coefficients. Simulations carried out on still images show the benefits which can be drawn from the proposed optimization techniques.

Many existing works related to lossy-to-lossless image compression are based on the lifting concept. However, it has been observed that the separable lifting scheme structure presents some limitations because of the separable processing performed along the image lines and columns. In this paper, we propose to use a 2D non separable lifting scheme decomposition that enables progressive reconstruction and exact decoding of images. More precisely, we focus on the optimization of all the involved decomposition operators. In this respect, we design the prediction filters by minimizing the variance of the detail signals. Concerning the update filters, we propose a new optimization criterion which aims at reducing the inherent aliasing artefacts. Simulations carried out on still and stereo images show the benefits which can be drawn from the proposed optimization of the lifting operators.

In this paper, we are interested in multicomponent image indexing in the Wavelet Transform (WT) domain. In this respect, the joint distribution of the WT coefficients through all the channels is modeled by a parametric copula-based model. The parameters of this model are considered as the salient signatures of the image content. The relevance of this model is based on a reliable choice of both the appropriate marginal distributions and the copula density reflecting the cross-component correlation. The similarity measure is chosen as the Kullback-Leibler divergence. The contribution of this work consists in proposing an organization of the features database in order to enable a coarse-to-fine resolution retrieval procedure suitable for progressive telebrowsing applications. Experimental results indicate that our new approach drastically reduces the retrieval time while maintaining acceptable retrieval performances.

In this paper, we develop a method to detect salient points at different scales in a given image. The principle of our approach is to consider a salient point as an outlier. Our contribution is twofold. The first novelty of our work consists of applying robust outliers statistical tests on the multiresolution representation of the underlying image. Besides, the second contribution relies on the exploitation of the interscale redundancies of the wavelet coefficients during the detection step. Experimental results carried out on real and synthetic images illustrate the performances of this new detection scheme.

Parallel magnetic resonance imaging (pMRI) relying on multiple receiver coils has emerged as a powerful 3D imaging technique for reducing scanning time or increasing spatial or temporal resolution. The acquired k-space is subsampled, and full field of view (FoV) images are then reconstructed from the acquired aliased data by applying methods such as the SENSE algorithm. However, reconstructed images using SENSE may suffer from several kinds of artifacts mainly because of noise and inaccurate sensitivity profiles. In this paper, we propose a regularized SENSE reconstruction method in which the regularization takes place in the wavelet transform domain. More precisely, a Bayesian strategy is adopted by introducing a bivariate prior to model the complex-valued signal. Experiments on synthetic data and real T1-weighted MRI images at 1.5 Tesla magnetic field show that the proposed method provides improved reconstruction.

Research in stereo image coding has focused on the disparity estimation/compensation process to exploit the cross-view redundancies. Most of the reported methods use a classical block-based technique in order to estimate the disparity field. However, this estimation technique does not always provide an accurate disparity map, which may affect the disparity compensation step. In this paper, we propose to use an estimation method that produces a dense and smooth disparity map. Then, on the one hand, this map is segmented and efficiently coded by exploiting the high correlation between neighboring disparity values. On the other hand, we integrate the disparity information into a vector lifting scheme for stereo image coding. Experimental results indicate that the proposed coding scheme outperforms the conventional methods employing a block-based disparity estimation.

In this paper, we are interested in multicomponent image indexing in the wavelet transform (WT) domain. More precisely, a WT is applied to each component then a suitable parametric model is retained for the distribution model of the wavelet coefficients. The parameters of this model are chosen as the salient features of the image content. The contribution of this work consists in choosing a parametric model which reflects the main dependencies existing between the resulting coefficients consisting of cross-component correlations and inter-scale similarities. The copula concept is introduced for building an appropriate statistical model of all the wavelet coefficients. Once the signatures are extracted, the retrieval procedure associated with a given query image is performed. Experimental results indicate that considering simultaneously the cross-component and the inter-scale correlation drastically improves the retrieval performances of the wavelet-based retrieval system.

In this work, we are interested in extracting salient signatures from multiscale representations of multispectral images for retrieval applications. The contribution of this paper consists in focusing on a special multiresolution decomposition based on the concept of Vector Lifting Scheme (VLS) which offers the advantage of simultaneously capturing the spatial and the cross-spectral redundancies of any multicomponent image. Within each subband, the joint distribution of the resulting coefficients stacked through the spectral components is modeled by a multivariate function driven by an appropriately chosen copula function. The parameters of such distribution model are chosen as relevant signatures of the image. Experimental results indicate an improvement in the retrieval performances when using the VLS instead of the conventional wavelet transform.

Many research efforts have been devoted to the improvement of stereo image coding techniques for storage or transmission. In this paper, we are mainly interested in lossy-to-lossless coding schemes for stereo images allowing progressive reconstruction. The most commonly used approaches for stereo compression are based on disparity compensation techniques. The basic principle involved in this technique first consists of estimating the disparity map. Then, one image is considered as a reference and the other is predicted in order to generate a residual image. In this paper, we propose a novel approach, based on vector lifting schemes (VLS), which offers the advantage of generating two compact multiresolution representations of the left and the right views. We present two versions of this new scheme. A theoretical analysis of the performance of the considered VLS is also conducted. Experimental results indicate a significant improvement using the proposed structures compared with conventional methods.

In this paper, we are interested in wavelet-based coding of 3D semi-regular meshes in order to ensure the progressiveness of the reconstruction. The contribution of this work relies on the adaptation procedure of the lifting scheme operators carried out at each resolution level. More precisely, we propose to firstly segment the original mesh into nonoverlapping regions. The involved predictors are then optimally computed for each region.

We propose a new estimator for image denoising using a 2D dual-tree M-band wavelet transform. Our work extends existing block-based wavelet thresholding methods by exploiting simultaneously coefficients in the two M-band wavelet trees. The contributions of this paper are two-fold. Firstly, we perform a statistical analysis of the noise in the considered redundant decomposition. Secondly, we propose an efficient method to remove the noise. Our approach relies on an extension of Stein's formula which allows us to take into account the specific correlations of the noise components. Simulation results are then presented to validate the proposed method

The paper presents the design of a multivariate statistical approach for multicomponent image denoising in the wavelet transform domain. We extend an approach that we have recently proposed, where the wavelet coefficients of all the image channels at the same spatial position, in a given orientation and at the same resolution level, are grouped into a vector, and a multivariate Bernoulli-Gaussian distribution is used as a prior model. The paper develops low-complexity maximum a posteriori rules that exploit jointly the intra- and interscale redundancies between the wavelet coefficients. Experimental results carried out on remote sensing multispectral images show that the proposed procedure improves the state-of-the-art wavelet-based denoising methods.

The objective of this paper is the design of adaptive quincunx lifting schemes for lossless compression of multiband images. More precisely, the operators of the lifting scheme are modified according to the local activity of the multivariate input signal. To this respect, a block-based adaptive strategy is adopted: the image is partitioned into a quadtree structure and a couple of optimal operators is assigned to each resulting volumetric segmented block. Our main contribution consists of a suitable quadtree partitioning rule that takes into account simultaneously the spatial and spectral redundancies. Simulations performed on real satellite images show that the proposed adaptive method outperforms the conventional non-adaptive lifting schemes.

Multichannel imaging systems provide several observations of the same scene which are often corrupted by noise. In this paper, we are interested in multispectral image denoising in the wavelet domain. We adopt a multivariate statistical approach in order to exploit the correlations existing between the different spectral components. Our main contribution is the application of Stein's principle to build a new estimator for arbitrary multichannel images embedded in additive Gaussian noise. Simulation tests carried out on optical satellite images show that the proposed method outperforms conventional wavelet shrinkage techniques.

Multichannel imaging systems provide several observations of the same scene which are often corrupted by additive noise. We are interested in multispectral image denoising in the wavelet domain. We adopt a multivariate approach in order to exploit the correlations existing between the different spectral components. Our main contribution is the application of Stein's principle to build a new estimator for arbitrary multichannel images embedded in Gaussian noise. Simulation tests carried out on multispectral satellite images show that the proposed method outperforms conventional wavelet shrinkage techniques.

In this letter, we revisit a number of concepts that have recently proven to be useful in multiresolution signal analysis, specifically by replacing the now classical linear-scale transition operators by nonlinear ones. More precisely, we address the problem of designing appropriate operators associated to nonlinear filter banks using multiscale analysis. We first establish a connection between nonlinear filter banks and partial differential equations operators used in scale-space theory. Toward this end, we propose specific structures of nonlinear three-band decompositions ensuring a perfect reconstruction. The behavior of the proposed structures is analyzed for a step-like signal in a high SNR scenario, and a simulation is proposed for a more complex scenario.

In this paper, we are interested in using multiwavelet transforms in the context of progressive and lossless coding of multi component images. More precisely, multiwavelet decompositions that map integers to integers are considered since they guarantee a perfect reconstruction in the absence of quantizers. Generally, these decompositions are performed separately on each spectral component of a multicomponent image. Therefore, they fail to exploit the spectral redundancies. Our main contribution in this paper consists in modifying multiwavelet decompositions in order to take into account simultaneously the spatial and the spectral redundancies contained in a multicomponent image. Simulation tests carried out on natural multicomponent images show that the the generalized interband decomposition outperforms the state-of-art lossless coders.

In this paper, a nonlinear subband decomposition scheme with perfect reconstruction is proposed for lossless and progressive coding of multispectral images. The merit of this new scheme is to exploit efficiently the spatial and the spectral redundancies contained in the multispectral images related to a scene of interest. Besides, the proposed method is suitable for telebrowsing applications. Experiments carried out on real scenes allow to assess its performances. The simulation results demonstrate that our approach leads to improved compression performances compared with currently used lossless coders.

A nonlinear subband decomposition scheme with perfect reconstruction is proposed for lossless coding of multispectral images. The merit of this new scheme is to exploit efficiently both the spatial and the spectral redundancies contained in a multispectral image sequence. Besides, it is suitable for progressive coding, which constitutes a desirable feature for telebrowsing applications. Simulation tests performed on real scenes allow assessment of the performances of this new multiresolution coding algorithm. The achieved compression ratios are higher than those obtained with currently used lossless coders.

This paper describes the use of polarimetric data for Earth terrain classification. The Cloude (1992) target decomposition theorem is applied to classify the scene into several classes having each one a distinct physical interpretation. The implemented algorithm, under its new version, uses two parameters, not often exploited in radar remote sensing, namely the entropy and a parameter linked to scattering mechanisms. The used data are polarimetric and multifrequency and are extracted from the Landes forest in France. The obtained results are satisfactory since one can understand the physical behavior of the wave when it is in contact with an obstacle.