基于小波滤波背景预测的红外弱小目标检测方法

红外弱小目标检测是红外图像研究领域的热点与难点。有效地从背景中检测出弱小目标对于后续的跟踪、识别工作具有十分重要的意义。针对现有检测方法的不足,提出了一种基于小波滤波背景预测的红外弱小目标检测方法。该方法利用小波滤波去噪的优良特性将目标作为噪声滤除,然后构建近似的前景分布图与背景分布图,最后基于连通体筛选与对比度门限完成弱小目标的提取。采用实测光电图像对该方法进行了验证,结果表明,提出的方法能够有效抑制噪声,完成背景预测以及红外弱小目标的检测。     

An interactive approach based on a discrete differential evolution algorithm for a class of integer bilevel programming problems

This paper presents an interactive approach based on a discrete differential evolution algorithm to solve a class of integer bilevel programming problems, in which integer decision variables are controlled by an upper-level decision maker and real-value or continuous decision variables are controlled by a lower-level decision maker. Using the Karush--Kuhn–Tucker optimality conditions in the lower-level programming, the original discrete bilevel formulation can be converted into a discrete single-level nonlinear programming problem with the complementarity constraints, and then the smoothing technique is applied to deal with the complementarity constraints. Finally, a discrete single-level nonlinear programming problem is obtained, and solved by an interactive approach. In each iteration, for each given upper-level discrete variable, a system of nonlinear equations including the lower-level variables and Lagrange multipliers is solved first, and then a discrete nonlinear programming problem only with inequality constraints is handled by using a discrete differential evolution algorithm. Simulation results show the effectiveness of the proposed approach.     

A commentary and correction on the article “Pansharpening by exploiting sharpness of the spatial structure”

This study clarifies the implicit potential deficiency caused by the sparse cardinality parameter k in Rong et al. (2014). In addition, k = β × W × M × N (0.9 ≤ β < 1) is suggested to avert this potential deficiency, where β is a ratio controlling the amount of sparse cardinality, W is the number of multispectral bands and M × N is the size of panchromatic image. With the choice of k suggested in this study, the low rank matrix L and sparse matrix S obtained by Go Decomposition (Zhou and Tao 2011) can be iteratively optimized and solved. Thus, instead of choosing k as W × M × N in Rong et al. (2014), the potential deficiency that L is directly obtained as an analytic solution can be averted.     

PolSAR image compression based on online sparse K-SVD dictionary learning

we present a novel polarimetric synthetic aperture radar (PolSAR) image compression scheme. PolSAR data contains lots of similar redundancies in single-channel and massively correlation between polarimetric channels. So these features make it difficult to represent PolSAR data efficiently. In this paper, discrete cosine transform (DCT) is adopted to remove redundancies between polarimetric channels, simple but quite efficient in improving compressibility. Sparse K-singular value decomposition (K-SVD) dictionary learning algorithm is utilized to remove redundancies within each channel image. Double sparsity scheme will be able to achieve fast convergence and low representation error by using a small number of sparsity dictionary elements, which is beneficial for the task of PolSAR image compression. Experimental results demonstrate that both numerical evaluation indicators and visual effect of reconstructed images outperform other methods, such as SPIHT, JPEG2000, and offline method.     

Region-driven distance regularized level set evolution for change detection in remote sensing images

Change detection is a fundamental task in the interpretation and understanding of remote sensing images. The aim is to partition the difference images acquired from multitemporal satellite images into changed and unchanged regions. Level set method is a promising way for remote sensing images change detection among the existed methods. Unfortunately, re-initialization, a necessary step in classical level set methods is known a complex and time-consuming process, which may limits their practical application in remote sensing images change detection. In this paper, we present an unsupervised change detection approach for remote sensing image based on an improved region-based active contour model without re-initialization. In order to eliminate the process for re-initialization and reduce the numerical errors caused by re-initialization, we describe an improving level set method for remote sensing images change detection. The proposed method introduced a distance regularization term into the energy function which could maintain a desired shape of the level set function and keep a signed distance profile near the zero level set. The experimental results on real multi-temporal remote sensing images demonstrate the advantages of our method in terms of human visual perception and segmentation accuracy.     

基于改进MC算法的医学图像三维重建研究

MC算法是经典的三维重建方法。但它重建时效率低,产生了大量的三角面片,增加了绘制的时间和空间。而且存在拓扑二义性,会使重建后的图像产生空洞的结构,重建的效果也不是很理想。对此,提出相应的改进策略。介绍了如何提高计算效率、减少三角面片数量、消除二义性和平滑图像等方面。通过实验证明了改进算法的可行性。     

采用混合时钟模式提高Linux时钟精度的方法

时钟精度直接影响到实时任务能否被及时响应和调度,数控系统要求其软件平台能提供微秒级的时钟精度。Linux操作系统由于其开放源代码的特点,非常适合开发具有自主产权的全软件数控系统,但是其毫秒级时钟精度明显过于粗糙。结合上述方法,提出一种混合多种时钟模式的动态时钟系统,提高Linux的时钟精度。通过仿真测试证明能满足数控系统的要求。     

Feature scaling for kernel fisher discriminant analysis using leave-one-out cross validation

Kernel fisher discriminant analysis (KFD) is a successful approach to classification. It is well known that the key challenge in KFD lies in the selection of free parameters such as kernel parameters and regularization parameters. Here we focus on the feature-scaling kernel where each feature individually associates with a scaling factor. A novel algorithm, named FS-KFD, is developed to tune the scaling factors and regularization parameters for the feature-scaling kernel. The proposed algorithm is based on optimizing the smooth leave-one-out error via a gradient-descent method and has been demonstrated to be computationally feasible. FS-KFD is motivated by the following two fundamental facts: the leave-one-out error of KFD can be expressed in closed form and the step function can be approximated by a sigmoid function. Empirical comparisons on artificial and benchmark data sets suggest that FS-KFD improves KFD in terms of classification accuracy.