N. Terki

Improved object tracking via joint color-LPQ texture histogram based mean shift algorithm

In this paper, a new robust mean shift tracker is proposed by utilizing the joint color and texture histogram. The contribution of our work is to take local phase quantization (LPQ) operator advantage of texture features representation, and to combine it with a color histogram mean shift tracking algorithm. The LPQ technique can be applied to obtain the texture features which represent the object. In texture classification, The LPQ operator is much robust to blur than the well-known local binary pattern operator (LBP). Compared with traditional color histogram mean shift algorithm which considers only color statistical information of the object, the joint color-LPQ texture histogram is more robust and overcome some difficulties of the traditional color histogram mean shift algorithm. Comparative experimental results on numerous challenging image sequences show that the proposed algorithm obtains considerably better performance than several state-of-the-art methods, especially traditional mean shift tracker. The algorithm is evaluated by numerical parameters: the center location and the average overlap, it proved the tracking robustness in presence of similar target appearance and background, motion blurring.

Intelligent control MPPT technique for PV module at varying atmospheric conditions using MATLAB/SIMULINK

Maximum power point tracking (MPPT) must usually be integrated with photovoltaic (PV) power systems so that the photovoltaic arrays are able to deliver the maximum power available. This paper proposes two methods of maximum power point tracking using a fuzzy logic and a neural network approach for photovoltaic (PV) module Kyocera KC200GT using MATLAB software. The two maximum power point tracking controllers receive solar radiation and photovoltaic cell temperature as inputs, and estimated the maximum power point and the current and voltage corresponding to it as outputs. The new method gives a good maximum power operation of any photovoltaic array under different conditions (varying atmospheric conditions) such as changing solar radiation and PV cell temperature. From the simulation results, the Neural Network approach can deliver more power and provides a response time response from the tracking system from the point of maximum power and pics lower than the fuzzy logic control.

Learning spatially correlation filters based on convolutional features via PSO algorithm and two combined color spaces for visual tracking

Last years, we have seen an emergence of wide methods in visual object tracking topic as convolutional neural network combined with correlation filter such as hierarchical features (HCF) (Ma et al. 20). However, upon the fact that some features may cause the tracking failures, the existing methods are still suffering of handling complex object appearance changes such as fast motion, significant deformation and occlusions. Further, they learn the correlation filter in frequency domain using Fourier transform, which cause unwanted boundary effects, which severely degrade the quality of the tracking model. Moreover, these methods are incapable of dealing with the illumination variation because they rely only on RGB base for color sequences. In this paper, we propose a novel method, which addresses the pre-cited problems. As first contribution, we learn adaptively three correlation filters in the spatial domain, with hierarchical convolutional features extracted from specific layers. Indeed, we apply the Particle Swarm Optimization algorithm to solve the update model equation of the correlation filters. Second, we propose that the switching between RGB and HSV color bases, give a soft manner to handle the illumination variation. For this aim, an HSV-energy condition is presented to choose the appropriate color base resorting to the energy of the second HSV component. Extensive experiments on a common benchmark dataset, justify that the proposed method outperforms the state-of-art methods.

Robust tracking with fuzzy sliding mod control strategy for grid connected photovoltaic system

This paper deals a grid-connected photovoltaic (PV) system that is composed of a PV array, boost converter with Robust Tracking Fuzzy sliding mode MPPT control strategy, and inverter coupled to grid. The MPPT control was performed using a hybrid control between the sliding mode control known for its simplicity and its position vis-à-vis robustness interference and control by fuzzy logic known by its fast response time and ease of implementation, in order to develop a MPPT controller that combines the performance of both commands. The proposed system with Fuzzy sliding mode MPPR control is tested using MATLAB/SIMULINK platform in which maximum power energy is tracked under constant and varying solar irradiance in to grid with a unity power factor. It can be concluded that the proposed method can quickly track the maximum power point of photovoltaic arrays, and also decrease the maximum power point oscillation energy loss. Therefore, the energy transmission efficiency of PV system power generation system is enhanced.

Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier

AbstractAs the state-of-the-art object trackers majority, hierarchical convolutional features (HCF) cannot recover tracking processes from problems of drifting caused by several challenges, especially by heavy occlusion, scale variation, and illumination variation. In this paper, we present a new effective method with the aim of treating these challenges robustly based on two principal tasks. First, we infer the target location using multichannel correlation maps, resulting from the combination of five learned correlation filters with convolutional features. In order to handle the illumination variation and get more rich features, we exploit an HSV energy condition to control the use of two color spaces, RGB and HSV. Second, we use the histogram of gradient features to learn another correlation filter in order to estimate the scale variation. Furthermore, we exploit an online training SVM classifier for target re-detecting in failure cases. The extensive experiments on a commonly used tracking benchmark dataset justify that our tracker significantly improves HCF and outperforms the state-of-the-art methods.

A new block matching algorithm based on stochastic fractal search

Block matching algorithm is the most popular motion estimation technique, due to its simplicity of implementation and effectiveness. However, the algorithm suffers from a long computation time which affects its general performance. In order to achieve faster motion estimation, a new block matching algorithm based on stochastic fractal search, SFS, is proposed in this paper. SFS is a metaheuristic technique used to solve hard optimization problems in minimal time. In this work, two main contributions are presented. The first one consists of computing the motion vectors in a parallel structure as opposed to the other hierarchical metaheuristic block matching algorithms. When the video sequence frame is divided into blocks, a multi-population model of SFS is used to estimate the motion vectors of all blocks simultaneously. As a second contribution, the proposed algorithm is modified in order to enhance the results. In this modified version, four ideas are investigated. The random initialization, usually used in metaheuristics, is replaced by a fixed pattern. The initialized solutions are evaluated using a new fitness function that combines two matching criteria. The considered search space is controlled by a new adaptive window size strategy. A modified version of the fitness approximation method, which is known to reduce computation time but causes some degradation in the estimation accuracy, is proposed to balance between computation time and estimation accuracy. These ideas are evaluated in nine video sequences and the percentage improvement of each idea, in terms of estimation accuracy and computational complexity, is reported. The presented algorithms are then compared with other well-known block matching algorithms. The experimental results indicate that the proposed ideas improve the block matching performance, and show that the proposed algorithm outperforms many state-of-the-art methods.

The effect of seasonal variation on the performances of grid connected photovoltaic system in southern of Algeria

This paper presents modeling, simulation, and analysis evaluation of the grid-connected PV generation system performance under MATLAB/Simulink. The objective is to study the effect of seasonal variation on the performances of grid connected photovoltaic system in southern of Algeria. This system works with a power converter. This converter allows the connection to the network and extracts maximum power from photovoltaic panels with the MPPT algorithm based on robust neuro-fuzzy sliding approach. The photovoltaic energy produced by the PV generator will be completely injected on the network. Simulation results show that the system controlled by the neuro-fuzzy sliding adapts to changing external disturbances and show their effectiveness not only for continued maximum power point but also for response time and stability.

An intelligent approach based on fuzzy logic for improving and optimizing the performance of a photovoltaic system

This work presents an intelligent approach to the improvement and optimization of control performance of a PV system, the method further maximum power point tracking (MPPT) based on fuzzy logic. Our system consists of a photovoltaic panel (PV), a DC-DC buck-boost converter, considered a matching stage between the PV and the load. The strategy for the synthesis of control laws is based on modeling the behavior of the PV system, which allows us to integrate different control techniques to ensure a smooth continuation in the presence of modeling errors and external disturbances. Modeling and simulation system (photovoltaic panel, Buck-Boost DC-DC converter, the MPPT algorithm based on fuzzy logic and load) is achieved through the Matlab / Simulink software.