Qiguang Miao

Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks

This paper presents a novel change detection approach for synthetic aperture radar images based on deep learning. The approach accomplishes the detection of the changed and unchanged areas by designing a deep neural network. The main guideline is to produce a change detection map directly from two images with the trained deep neural network. The method can omit the process of generating a difference image (DI) that shows difference degrees between multitemporal synthetic aperture radar images. Thus, it can avoid the effect of the DI on the change detection results. The learning algorithm for deep architectures includes unsupervised feature learning and supervised fine-tuning to complete classification. The unsupervised feature learning aims at learning the representation of the relationships between the two images. In addition, the supervised fine-tuning aims at learning the concepts of the changed and unchanged pixels. Experiments on real data sets and theoretical analysis indicate the advantages, feasibility, and potential of the proposed method. Moreover, based on the results achieved by various traditional algorithms, respectively, deep learning can further improve the detection performance.

Linear Feature Separation From Topographic Maps Using Energy Density and the Shear Transform

Linear features are difficult to be separated from complicated background in color scanned topographic maps, especially when the color of linear features approximate to that of background in some particular images. This paper presents a method, which is based on energy density and the shear transform, for the separation of lines from background. First, the shear transform, which could add the directional characteristics of the lines, is introduced to overcome the disadvantage that linear information loss would happen if the separation method is used in an image, which is in only one direction. Then templates in the horizontal and vertical directions are built to separate lines from background on account of the fact that the energy concentration of the lines usually reaches a higher level than that of the background in the negtive image. Furthermore, the remaining grid background can be wiped off by grid templates matching. The isolated patches, which include only one pixel or less than ten pixels, are removed according to the connected region area measurement. Finally, using the union operation, the linear features obtained in different sheared images could supplement each other, thus the lines of the final result are more complete. The basic property of this method is introducing the energy density instead of color information commonly used in traditional methods. The experiment results indicate that the proposed method could distinguish the linear features from the background more effectively, and obtain good results for its ability in changing the directions of the lines with the shear transform.

Network Structural Balance Based on Evolutionary Multiobjective Optimization: A Two-Step Approach

Research on network structural balance has been of great concern to scholars from diverse fields. In this paper, a two-step approach is proposed for the first time to address the network structural balance problem. The proposed approach involves evolutionary multiobjective optimization, followed by model selection. In the first step, an improved version of the multiobjective discrete particle swarm optimization framework developed in our previous work is suggested. The suggested framework is then employed to implement network multiresolution clustering. In the second step, a problem-specific model selection strategy is devised to select the best Pareto solution (PS) from the Pareto front produced by the first step. The best PS is then decoded into the corresponding network community structure. Based on the discovered community structure, imbalanced edges are determined. Afterward, imbalanced edges are flipped so as to make the network structurally balanced. Extensive experiments on synthetic and real-world signed networks demonstrate the effectiveness of the proposed approach.

A Memetic Multi-objective Immune Algorithm for Reservoir Flood Control Operation

Reservoir flood control operation (RFCO) is a challenging optimization problem with multiple conflicting decision goals and interdependent decision variables. With the rapid development of multi-objective optimization techniques in recent years, more and more research efforts have been devoted to optimize the conflicting decision goals in RFCO problems simultaneously. However, most of these research works simply employ some existing multi-objective optimization algorithms for solving RFCO problem, few of them considers the characteristics of the RFCO problem itself. In this work, we consider the complexity of the RFCO problem in both objective space and decision space, and develop an immune inspired memetic algorithm, named M-NNIA2, to solve the multi-objective RFCO problem. In the proposed M-NNIA2, a Pareto dominance based local search operator and a differential evolution inspired local search operator are designed for the RFCO problem to guide the search towards the and along the Pareto set respectively. On the basis of inheriting the good diversity preserving in immune inspired optimization algorithm, M-NNIA2 can obtain a representative set of best trade-off scheduling plans that covers the whole Pareto front of the RFCO problem in the objective space. Experimental studies on benchmark problems and RFCO problem instances have illustrated the superiority of the proposed algorithm.

A denoising algorithm via wiener filtering in the shearlet domain

An image denoising algorithm via wiener filtering in the shearlet domain is proposed in this paper, it makes full use of the advantages of them. Shearlets have the features of directionality, localization, anisotropy and multiscale, the image can be decomposed more accurately, and the noise information locates at the high frequency contents in the frequency spectrum, which can help the removal of noise. The wiener filtering is based on minimizing the mean square error criteria; and it has a good performance on removing the Gaussian white noise. So the combination between them can remove noise more effectively. The noisy image is decomposed by the shearlet transform at any scales and in any directions firstly, the high and low frequency coefficients are thus acquired. And then, in the shearlet domain, the high frequency parts are filtered by wiener filtering. Finally, the inverse shearlet transform is adopted to obtain the denoised image. At the end of paper, the experiments show that the proposed algorithm could get better results than others.

Optimizing dynamical changes of structural balance in signed network based on memetic algorithm

Abstract In dynamical evolution of structural balance, unbalanced signed networks evolve to structurally balanced ones. In this paper, we compute the least number of sign changes in the evolution of structural balance. It is suggested that there be a certain bias towards flipping positive or flipping negative signs. The number of flipped signs is quantified by an objective function. Moreover, a memetic algorithm is proposed to optimize the objective function. Experiments show that our algorithm is efficient and effective to optimize dynamical evolution of structural balance.

Self-adaptive multi-objective evolutionary algorithm based on decomposition for large-scale problems

Large-scale multi-objective optimization problems (LS-MOP) are complex problems with a large number of decision variables. Due to its high-dimensional decision space, LS-MOP poses a significant challenge to multi-objective optimization methods including multi-objective evolutionary algorithms (MOEAs). Following the algorithmic framework of multi-objective evolutionary algorithm based on decomposition (MOEA/D), an enhanced algorithm with adaptive neighborhood size and genetic operator selection, named self-adaptive MOEA/D (SaMOEA/D), is developed for solving LS-MOP in this work. Learning from the search history, each scalar optimization subproblem in SaMOEA/D varies its neighborhood size and selects a genetic operator adaptively. The former determines the size of the search scope, while the latter determines the search behavior and as a result the newly generated solution. Experimental results on 20 LS-MOP benchmarks have demonstrated that SaMOEA/D outperforms or performs similarly to the other four state-of-the-art MOEAs. The effectiveness of the self-adaptive strategies has also been experimentally verified. Furthermore, SaMOEA/D and the comparing algorithms are then applied to solve a challenging real-world problem, the multi-objective reservoir flood control operation problem. Optimization results illustrate the superiority of SaMOEA/D.

Superpixel-Based Difference Representation Learning for Change Detection in Multispectral Remote Sensing Images

With the rapid technological development of various satellite sensors, high-resolution remotely sensed imagery has been an important source of data for change detection in land cover transition. However, it is still a challenging problem to effectively exploit the available spectral information to highlight changes. In this paper, we present a novel change detection framework for high-resolution remote sensing images, which incorporates superpixel-based change feature extraction and hierarchical difference representation learning by neural networks. First, highly homogenous and compact image superpixels are generated using superpixel segmentation, which makes these image blocks adhere well to image boundaries. Second, the change features are extracted to represent the difference information using spectrum, texture, and spatial features between the corresponding superpixels. Third, motivated by the fact that deep neural network has the ability to learn from data sets that have few labeled data, we use it to learn the semantic difference between the changed and unchanged pixels. The labeled data can be selected from the bitemporal multispectral images via a preclassification map generated in advance. And then, a neural network is built to learn the difference and classify the uncertain samples into changed or unchanged ones. Finally, a robust and high-contrast change detection result can be obtained from the network. The experimental results on the real data sets demonstrate its effectiveness, feasibility, and superiority of the proposed technique.

A new artistic information extraction method with multi channels and guided filters for calligraphy works

The artistic beauty of Chinese calligraphy is constituted by two elements: form and spirit . To learn and study calligraphy works, both of form and spirit should be extracted correctly. However, most currently used calligraphy image extraction methods can only obtain form information. To address this problem, an extraction method, based on multi-channel and guided filters, is proposed in this study. The proposed method consists of three major operations: color space transformation, tablet and writing discrimination, and information extraction using guided filter. To simulate the human visual perception of calligraphy work, the color space of a calligraphy image is converted from RGB to CIELAB firstly. Then the calligraphy image is distinguished as either a tablet or a writing based on channel b. Finally, information extraction using guided filter is performed. For a tablet, a two-stage guided filtering strategy based on L channel is employed to reduce noise and obtain form information. For a writing, a guided filter based on channels L and a is used to extract both form and spirit information. To demonstrate the accuracy and efficiency of the proposed method, comparison experiments are implemented on both types of images. Experimental results reveal the advantages of the proposed method.

Guided Superpixel Method for Topographic Map Processing

Superpixels have been widely used in lots of computer vision and image processing tasks but rarely used in topographic map processing due to the complex distribution of geographic elements in this kind of images. We propose a novel superpixel-generating method based on guided watershed transform (GWT). Before GWT, the cues of geographic element distribution and boundaries between different elements need to be obtained. A linear feature extraction method based on a compound opposite Gaussian filter and a shear transform is presented to acquire the distribution information. Meanwhile, a boundary detection method, which based on the color-opponent mechanisms of the visual system, is employed to get the boundary information. Then, both linear features and boundaries are input to the final partition procedure to obtain superpixels. The experiments show that our method has the best performance in shape control, size control, and boundary adherence, among all the comparison methods, which are classic and state of the art. Furthermore, we verify the low complexity and low cost of memory in our method through experiments, which makes it possible to deal with large-scale topographic maps.