Search

Super-resolution (SR) based on deep learning has been playing an important role in improving the spatial resolution of remote sensing images. Although convolutional neural networks (CNNs) dominate the research of remote sensing image SR, most of them struggle to fully utilize the multilevel features in information transmission. Constantly expanding the network architecture sometimes also leads to an increase in feature redundancy and computational complexity. Moreover, CNN-based methods are unable to generate visually appealing images. To address the aforementioned issues, we propose a multilevel feature fusion attention SR method based on GAN called MFFAGAN. Specifically, we propose a novel enhanced mixed-attention block (EMAB), which enables the network to capture key feature information in both the channel and spatial domains. Meanwhile, in order to enhance the model's ability to extract various features at multiple levels more efficiently, we propose a multilevel feature fusion attention module (MFFAM). The output of each residual block is directly fed into the feature aggregation block and eventually combined with the attention branch. Thus, the network is capable of aggregating these information-rich residual features without any loss to produce more representative features. Experimental results show that our proposed MFFAGAN outperforms most state-of-the-art methods in both quantitative and qualitative metrics.

Block pulse functions (BPFs) are piecewise constant and not sufficiently smooth. Therefore, their accuracy is limited when it comes to identifying the parameters of fractional order systems (FOSs). This in turn means that BPFs are incapable of offering highly accurate parameter identification results. However, using a great number of BPFs would significantly increase the dimension of the operational matrix and thereby adds to the computational complexity and burden. To overcome this problem, we present here a hybrid function method for identifying FOSs. The method utilizes a hybrid of Bernoulli polynomials and block pulse functions (HBPBPFs) as the base functions to approximate input and output signals. The fractional integral operational matrix of HBPBPFs is derived and used to convert an FOS to an algebraic system. The parameters of the FOS are successfully identified by minimizing the mean square error between the output of the true system and that of the algebraic representation of the FOS. The simulation experiment verifies that our proposed HBPBPFs method is effective and can generate more accurate identification results than existing BPFs methods.

As a position servo system to isolate disturbance from its carrier, stabilized platform requires high-precision and high-adaptability control. However, conventional integer-order PID (IOPID) control fails to meet that requirement. In this paper, a new controller design scheme is proposed for stabilized platform based on fractional calculus. The designed controller is called fractional-order PID (FOPID) controller, which has two extra parameters compared to conventional PID controller. On one hand, it provides more degrees of freedom to design FOPID controller. On the other hand, its differential order and integral order provides more flexibility to tune the controller performance. Therefore, a design method of FOPID controller based on dynamic software modeling is presented. To obtain the ideal controller's parameters, the particle swarm optimization (PSO) bionic algorithm is used to optimize an objective function. In addition, software simulation platform and hardware experiment system are built to design and test the FOPID controller. Finally, the results of simulation and experiment are included to show the effectiveness of the new control method.

To improve the segmentation performance of thresholding methods, a novel strategy of integrating the spatial information between pixel's is proposed in this paper. The proposed strategy utilizes pixel's gray level and its local entropy within a neighborhood to construct a novel 2-D histogram, called gray level-local entropy (GLLE) histogram. The local entropy can effectively reflect the homogeneity of a pixel's gray level in a neighborhood. Based on the GLLE histogram, an ideal thresholding vector is obtained by maximizing the total Tsallis entropy of background and objects. The proposed method is validated through segmenting several real images. Experimental results show that the proposed method outperforms many existing thresholding methods.

In this paper, the parameter identification issue of fractional-order chaotic system with time delay is studied, which is important for its modelling and controlling. A numerical algorithm for fractional differential equation with time delay is given. Time delay and fractional order along with other ordinary parameters are estimated together, which is rarely considered before. The identification issue is converted to an optimization problem, which is nonlinear, multivariable and multimodal. To solve this complex optimization problem effectively, a multi-selection differential evolution (MS-DE) is proposed. In MS-DE, multiple vectors are generated as candidate for selection, which can avoid the local extremum and speed up the convergence speed. The simulation results illustrate the effectiveness of the proposed MS-DE method.

In this paper, a new method is proposed for prediction of ship roll motion based on extreme learning machine (ELM). To improve the prediction accuracy and avoid over or under fitting, two techniques are adopted to select the appropriate structure of ELM. First, the inputs of the ELM are selected from the roll motion time series using Lipschitz quotient method. Second, the number of hidden layer nodes is determined via ℓ1 regularized technique. Finally, the ℓ1 regularized ELM is solved by least angle regression (LAR) algorithm. The effectiveness of the proposed method is demonstrated by ship roll motion prediction experiments based on the real measured ship roll motion time series.

Spatial correlation information between pixels is considered to be very important in thresholding methods. However, it is often ignored and thus unsatisfied segmentation results maybe obtained. To overcome this shortcoming, we propose a new image segmentation approach by taking not only pixels’ spatial information but also pixels’s gray level into account. First, a non-local mean filter is imposed on the image. Then the filtered image and the original image together are adopted to build a two dimensional histogram, it is called non-local mean two dimensional histogram. Finally, a minimum relative entropy criteria is used to select the ideal thresholding vector. Since the non-local mean filter process is performed in a neighborhood of current pixel, it carries out the spatial information of current pixel. Segmentation results on several images illustrate the effectiveness of the proposed thresholding method, whose segmentation accuracy are greatly improved compared to most existing thresholding methods.

Thresholding is a popular method of image segmentation. Many thresholding methods utilize only the gray level information of pixels in the image, which may lead to poor segmentation performance because the spatial correlation information between pixels is ignored. To improve the performance of thresolding methods, a novel two-dimensional histogram—called gray level-local variance (GLLV) histogram—is proposed in this paper as an entropic thresholding method to segment images with bimodal histograms. The GLLV histogram is constructed by using the gray level information of pixels and its local variance in a neighborhood. Local variance measures the dispersion of gray level distribution of pixels in a neighborhood. If a pixel’s gray level is close to its neighboring pixels, its local variance is small, and vice versa. Therefore, local variance can reflect the spatial information between pixels. The GLLV histogram takes not only the gray level, but also the spatial information into consideration. Experimental results show that an entropic thresholding method based on the GLLV histogram can achieve better segmentation performance.