Referring Image Segmentation (RIS) aims to accurately match specific instance objects in an input image with natural language expressions and generate corresponding pixel-level segmentation masks. Existing methods typically obtain multi-modal features by fusing linguistic features with visual features, which are fed into a mask decoder to generate segmentation masks. However, these methods ignore interfering noise in the multi-modal features that will adversely affect the generation of the target segmentation masks. In addition, the vast majority of current RIS models incorporate only a residual structure derived from a block within the Transformer model. The limitations of this information propagation approach hinder the stratification of the model structure, consequently affecting the training efficacy of the model. In this paper, we propose a RIS method called DSFRIS, which combines the knowledge of sparse reconstruction and employs a novel training mechanism in the process of training the decoder. Specifically, we propose a feature distillation mechanism for the multi-modal feature fusion stage and a feature supplementation mechanism for the mask decoder training process, which are two novel mechanisms for reducing the noise information in the multi-modal fusion features and enriching the feature information in the decoder training process, respectively. Through extensive experiments on three widely used RIS benchmark datasets, we demonstrate the state-of-the-art performance of our proposed method.

Aiming at the problem that the current defocus blurred region detection methods are easy to misjudge homogeneous-sharp regions, and can′t locate the edge accurately enough, a defocus blurred region detection method based on LBP and saliency is proposed. Firstly, LBP feature and SLIC algorithm are used to obtain SLBP blur map, DRFI saliency detection algorithm is used to obtain DRFI saliency map. Secondly, the trimap is obtained using SLBP blur map and DRFI saliency map, and then KNN matting algorithm is used to obtain a blur map. Finally, the blur map is refined with the help of morphological operations and smoothing filter. The experimental results on the public blur dataset show that the method can effectively detect homogeneous-sharp regions, retain the edge details of an image, and perform well in detection accuracy and recall.

论述了电子信息类专业中"数字信号处理"课程的重要性,详细分析了"数字信号处理"课程教学中存在的问题,探讨了案例式教学法在"数字信号处理"课程中的设计思路,并针对课程中的主要教学内容给出了具体的教学实施方案,最后选取课程中比较典型的两个工程案例,详细阐述了案例教学法的具体实施过程.教学实践证明将案例式教学法引入教学中,通过实际工程应用案例的讨论与实践,能充分调动学生学习的主观能动性,提高学生对数字信号处理的综合应用能力.

Dual-channel contrast prior (Dual-CP) simulates contrast using the difference between the bright channel and the dark channel of an image, and it achieves good results in the blind restoration of blurred images. However, in practical applications, the values of the bright channel and the dark channel of an image are not distributed on 1 and 0 as theoretically researched. This paper proposes a blind image restoration algorithm that combines Dual-CP, L-0 regularization strength, and gradient prior, wherein an effective optimization algorithm is derived using semi-quadratic splitting method to solve the nonconvex L-0 minimization problem. Experiments demonstrate that the proposed method has better intuitive description recovery capabilities, and on the benchmark dataset presented by Levin et al., Kohler et al., and Lai et al., the average peak signal-to-noise ratio increased by 2. 1051 dB, 1. 1273 dB, and 0. 4491 dB, respectively, and the average structural similarity increased by 0. 1302, 0. 0599, and 0. 0158, respectively.

针对面部动力谱(FDM)特征易受光照影响、对运动信息描述不准确的缺陷,提出基于FDM特征与时空局部二值模式积分投影(STLBP-IP)特征相结合的微表情识别方法.将FDM特征与STLBP-IP特征相结合,在弥补FDM对运动信息描述不足的同时对人脸面部信息进行补充描述以提升识别率.使用支持向量机进行分类,在SMIC和CASMEⅡ微表情数据库上进行实验.实验结果表明,该算法识别率有所提高,分别达到57.14％和64.59％.

Single image blind motion deblurring refers to transferring a blurred motion image into a corresponding clear image, which is a challenging and classic problem in the field of computer vision. The spatially variant blur is usually caused by many factors, such as camera jitter and object motion. Since image deblurring can be regarded as the task of image transformation, deep learning methods based on coarse-to-fine scheme, especially those using multi-scale architectures become popular. However, they have the disadvantages of unsatisfactory image quality and time-consuming running caused by large kernel size. In this paper, we propose a novel end-to-end network structure based on Deep Hierarchical Multi-patch network architecture integrated with Context Module and additional ResBlocks in order to tackle deblurring problem. Compared with recently proposed networks, it generates images with better visual effect as well as higher image quality index. Besides, our model significantly reduces the test time. We evaluate the proposed network structure on public GoPro dataset, a large-scale image dataset with complex synthetic blur. The experiments on the benchmark dataset prove that our effective method outperforms other state-of-the-art blind deblurring algorithms both qualitatively and quantitatively, which demonstrates the effectiveness of Context Module in the task of single image blur removal.

文章论述了在电子信息类专业中开展"数字信号处理"课程双语教学的重要性和必要性,详细分析了"数字信号处理"课程双语教学中存在的问题,通过在教材选用、教学内容、教学模式及考核方式四个方面的改革及实践,使得教学效果得到有效提升,并总结和分析了教学改革的成效.

筒中筒结构是超高层建筑最常用的结构形式之一.结构在水平力作用下,由内筒抗侧刚度大和外筒抗侧刚度小而引起的内外筒效应分配不协调,导致在各水准地震作用下内外筒不能有效协同工作.介绍了一种新型超高层装配整体钢网格盒式“筒中筒”混合结构的构造形式,并以一拟建超高层结构为例,运用有限元分析软件,对比分析了新结构与常规结构内外筒剪力分配和外筒的抗侧刚度.研究表明,在梁柱截面减小的条件下,相比常规结构,新型结构外筒能分配更多的楼层剪力,外筒的抗侧刚度明显大于常规结构,新结构内外筒的协同工作能力更好.

In general blind restoration algorithms,only the gray information of a color image is utilized to estimate the blurring kernel,and thus a restored image may be unsatisfactory if its size is too small or the salient edge in it is too little.Focused on the above mentioned problem,a new blind image restoration algorithm was proposed under a new tensorial framework,in which a color image was regarded as a third-order tensor.First,the blurring kernel was estimated utilizing the multi scale edge information of blurred color image which could be obtained by adjusting the regularization parameter in tensorial total variation model.Then a deblurring algorithm based on tensorial total variation was adopted to recover the latent image.The experimental results show that the proposed algorithm can achieve obvious improvement on Peak Signal-to-Noise Ratio (PSNR) and subjective vision.

基于贵州省湄潭县、金沙县和施秉县543名土地流转农户的问卷调查,实证分析了“差序格局”社会关系对农地流转契约选择的影响.研究结果表明:“差序格局”关系显著影响到契约形式选择,血缘和地缘越接近,农户越倾向选择口头契约.当农户拥有党员身份、土地流转年份越近、流转土地面积越大和租金为货币形式时,农民则越可能选择书面契约.进一步分析表明,转出户受到了血缘和地缘关系双重影响,而转入户只受到地缘关系影响,“差序格局”对两种农户的影响存在差异.

Point spread function (PSF) estimation plays a paramount role in image deblurring processing, and traditionally it is solved by parameter estimation of a certain preassumed PSF shape model. In real life, the PSF shape is generally arbitrary and complicated, and thus it is assumed in this manuscript that a PSF may be decomposed as a weighted sum of a certain number of Gaussian kernels, with weight coefficients estimated in an alternating manner, and an l(1) norm-based total variation (TVl(1)) algorithm is adopted to recover the latent image. Experiments show that the proposed method can achieve satisfactory performance on synthetic and realistic blurred images.

随着城镇化进程的推进，贵州出现了农村实际劳动人口锐减的情况，为适应现代生产力的发展，发挥资源的集聚优势，提高农业的抗风险能力，对贵州省农地适度规模经营的制约因素进行分析，为推进贵州省农地适度规模经营提出一些可行性建议。

The deblurring algorithm based on the total variation (TV) model can better preserve sharp edges. However, the existing algorithms could not really deal with the multichannel images. In this paper, we extend the general TV model in matrix space to tensor TV model in third-order tensor space, called as t-TV model, utilizing a new tensor product, t-product. And an efficient algorithm, based on alternating minimization, is adopted to solve the t-TV model. The proposed method retains the advantages of the general TV regularization. Meanwhile it could directly deal with the multichannel images in tensor framework. Experimental results show that the proposed method can achieve satisfactory performance on gray and color blurred images.

This paper presents a wireless and intelligent shot marking system,which is made up of camera,portable computer and wireless router.The system can realize the intelligent marking used algorithm of image identification.The design has the characteristic of portable and high cost performance.The shot hole can be automatic recognition through image preprocessing,auto-select thresholds and contour extraction.

The restoration quality of a motion-blurred image is highly dependent on the estimation accuracy of the motion blurring parameter. This manuscript presents a novel and precise method for estimation of the motion blurring length, wherein the ringing artifact amount of a deblurred image is measured by energy proportion contained in appropriate frequency bands, and a blurring length with minimum ringing artifact amount is taken as the optimal estimation of the true blurring length. Experimental results show good performance of the proposed algorithm in motion blurring length estimation.

Base on the image sparse decomposition,according to the different characters of image and noise in sparse decomposition,proposed a model based on asymmetric atomic atoms library,by algorithm the acquisition of effective de-noising analysis of gray images.Denoising to improve image PSNR values,and has a better visual effect.Will be collected by digital image denoising cloth blank background and the defects after separation in order to more effectively define the defects in order to facilitate the follow-up of the relevant characteristics of extraction.Experimental results show that :in comparison with the wavelet based denoising methods,our learning based algorithm has better denoising ability,keep more detail image information and improve the peak signal to noise ratio.

Motion estimation is one of the basic problems in digital video processing; it is significant in the applications of video image compression, registration, mosaic, and target detection, and so on. In the base of discussing basic phase correlation algorithm, a method based on kernel regression for constructing two-dimensional circular symmetry window function has been introduced, and the improved scheme based on windowed preprocessing, is proposed for translational motion estimation of moving object. Experimental results show the feasibility of the presented scheme.

In the scale-invariant feature transform (SIFT) algorithm, directional stability is a significant factor which affects the matching results between key points. This paper proposes adaptive kernel regression function as a replacement for the original Gaussian function in order to weigh the gradient direction around the key points for image registration. The gradient information is included in the weighting function. For changes in flat areas, the weight function is shaped as a circle-like function while in edged areas it is shaped as ellipsoid-like function. More stability between key points is achieved with the adaptive weight function. More stabile direction of key point is got. Some experimental results on standard test set of image registration show the feasibility of this method.

This paper presents a new method to ascertain the position of embedding bytes according to the size of cover image,embedding capacity and random function.The embedding information is distributed evenly.The secret information is hiding though the properties of XOR operation and the features of bit planes.The algorithm makes the two secret information bits embed into a pixel,but only need change one bit at most.It can enhance the embedding capacity and the secret information can be recovered with no change.The experimental results show that this method is available and efficient.