Hamid Tairi

3D extension of the fast and adaptive bidimensional empirical mode decomposition

The Bidimensional Empirical Mode Decomposition (BEMD) has taken its place among the most known decomposition methods as Fourier transform and wavelet, but the enormous execution time that it requires represents a real obstacle for its application. Hence the Fast and Adaptive Bidimensional Empirical Mode Decomposition (FABEMD) is proposed basically to overcome this obstacle by decreasing the execution time of the BEMD; its principle is based on the use of statistical filters to generate the upper and the lower envelopes instead of the interpolation functions used in the BEMD. In this work we propose a 3D extension of the FABEMD denoted Fast and Adaptive Tridimensional Empirical Mode Decomposition which can decompose a volume into a set of Tridimensional Intrinsic Mode Functions (TIMFs), the first TIMFs belong to the high frequencies and the last ones to the low frequencies. The proposed approach takes an efficient runtime compared with the considerable one required by the Multidimensional Ensemble Empirical Mode Decomposition, and it ensures a good quality of the decomposition in term of orthogonality and reconstruction. The obtained results are encouraging and will open a new road to three dimensional extensions of many applications.

Implementing a Fuzzy Logic Based Algorithm to Predict Solar and Wind Energies in a Hybrid Renewable Energy System

The use of multi sources systems of energy progressed significantly in different industrial sectors. Between all the existing sources of energy, batteries and renewable sources, such as photovoltaic and wind, contain the highest specified energy. However, solar and wind energies are not available all the time, their performance is affected by unpredictable weather changes and therefore, it is difficult to control as it is not always feasible to obtain an accurate mathematical model of the controlled system. Also, uncertainty of the wind power can affect system stability. This paper presents a computer algorithm based on fuzzy logic control FLC to estimate the wind and solar energies in a hybrid renewable energy system from natural factors. The wind power was estimated using the wind speed as an input parameter and the solar power was estimated using the temperature and the lighting as input parameters.

An image registration algorithm based on phase correlation and the classical Lucas–Kanade technique

Image registration is defined as an important process in image processing in order to align two or more images. A new image registration algorithm for translated and rotated pairs of 2D images is presented in order to achieve subpixel accuracy and spend a small fraction of computation time. To achieve the accurate rotation estimation, we propose a two-step method. The first step uses the Fourier Mellin Transform and phase correlation technique to get the large rotation, then the second one uses the Fourier Mellin Transform combined with an enhance Lucas–Kanade technique to estimate the accurate rotation. For the subpixel translation estimation, the proposed algorithm suggests an improved Hanning window as a preprocessing task to reduce the noise in images then achieves a subpixel registration in two steps. The first step uses the spatial domain approach which consists of locating the peak of the cross-correlation surface, while the second uses the frequency domain approach, based on low-frequency (aliasing-free part) of aliased images. Experimental results presented in this work show that the proposed algorithm reduces the computational complexities with a better accuracy compared to other subpixel registration algorithms.

Hybrid strategy based on MAS for an intelligent energy management: Application to an electric vehicle

This article proposes a multi-agent approach for managing electric vehicle energy. The vehicle power source consists of a Lithium Metal Polymer (LMP) battery and a Super-capacitor. The adopted management strategy is a hybrid strategy, based on three techniques of artificial intelligence, on the fuzzy logic and the genetic algorithms on one hand, on the other hand, on the multi-agent systems. These main methods were combined in the developed system to carry out the management task. The fuzzy inference system is first optimized off-line by the genetic algorithm. Then it is used during on-line checking to take into account the uncertain case. The architecture of our system is based on the agents, they have been applied to distribute the control tasks and locate accordingly the command of the components of the hybrid electrical source. During the simulation tests (on the New European Driving Cycle NEDC) we succeeded, due to the results, to achieve the objective of this work; indeed the system works effectively with the used method. Thus, the hybrid strategy is operational, and it realizes an important sheath in terms of energy, that is to say a longer autonomy of electric vehicle.

Motion detection using color structure-texture image decomposition

Analyzing and interpreting video is a growing topic in computer vision and its applications. This paper mainly contributes to the Color Space-Time Interest Points (CSTIP) extraction and detection. We propose a new method for detection of moving objects. Two main steps compose the proposed method. First, we suggest applying the algorithm of the detection of Color Space-Time Interest Points (CSTIP) on both components of the Color Structure - Texture Image Decomposition which is based on a Partial Differential Equation (PDE): a color geometric structure component and a color texture component. A descriptor is associated to each of these points. In a second stage, we address the problem of grouping the points (CSTIP) into clusters. Experiments and comparison to other motion detection methods on challenging sequences show the performance of the proposed method and its utility for video analysis. Experimental results are obtained from very different types of videos, namely sport videos and animation movies.

Motion Detection Using Color Space-Time Interest Points

Detecting moving objects in sequences is an essential step for video analysis. Among all the features which can be extracted from videos, we propose to use Space-Time Interest Points (STIP). STIP are particularly interesting because they are simple and robust low-level features providing an efficient characterization of moving objects within videos. In general, Space-Time Interest Points are based on luminance, and color has been largely ignored. However, the use of color increases the distinctiveness of Space-Time Interest Points. This paper mainly contributes to the Color Space-Time Interest Points (CSTIP) extraction and detection. To increase the robustness of CSTIP features extraction, we suggest a pre-processing step which is based on a Partial Differential Equation (PDE) and can decompose the input images into a color structure and texture components. Experimental results are obtained from very different types of videos, namely sport videos and animation movies.

Motion estimation using the total variation-local-global optical flow and the structure-texture image decomposition

Motion estimation is currently approximated by the visual displacement field called optical flow. The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. Actually, several methods are used to estimate the optical flow, but a good compromise between computational cost and accuracy is hard to achieve. This work presents a combined local-global-total variation CLG-TV approach with structure-texture image decomposition. The combination is used to control the propagation phenomena and to gain robustness against illumination changes, influence of texture on the results and sensitivity to outliers. The resulting method is able to compute larger displacements in a reasonable time.

Visual object tracking via the local soft cosine similarity

Abstract In this paper, we propose a robust visual tracking algorithm based on soft similarity under the Bayesian framework. Firstly, we propose a Local Soft Similarity based on Soft Cosine Measure (L3SCM) that measures the soft similarity between two vectors of features in Vector Space Model (VSM) by taking into account dependencies between these features. Secondly, we model the motion model component of the proposed tracker by using the Bayesian framework, then we apply the L3SCM measure into the observation model component to measure the local similarities between the template of the tracked target and the sampled candidates in incoming frame of a given image sequence. Finally, we integrate a simple scheme to update the target template throughout the tracking process in order to improve the robustness of the proposed tracker. Experimental results on several challenging image sequences illustrate that the proposed method performs better against several state-of-the-art trackers.

Visual tracking of a moving object via the soft cosine measure

In this paper, we propose a Local Soft Similarity based on Soft Cosine Measure (L3SCM) and then we incorporate it into visual tracking framework. Firstly, we present the soft cosine measure that measures the soft similarity between two vectors of features by taking into consideration similarities of pairs of features. Secondly, we apply this soft similarity in the observation model component of the proposed tracker to measure the local similarities between the template of the tracked target and the sampled candidates. Finally, in order to improve the robustness of the proposed tracker, we integrate a simple scheme to update the target template throughout the tracking process. Experimental results on several challenging image sequences illustrate that the proposed method performs better against several state-of-the-art trackers.

Hybrid method for background modeling and subtracting

In this paper, we propose a hybrid method for background modeling, subtracting, and extracting moving objects, which is based on the use of W4 and Extended Centre Symmetric Local Binary Pattern (XCS-LBP) approaches. Initially, we apply W4 to get the foreground mask of the video scene, after that we use XCS-LBP to clarify the results obtained. The main focus of this paper is to illustrate moving objects. In the evaluation section, we will prove that the proposed hybrid method gives better results than W4 with the use of datasets contains a different background.