多光谱图像融合中小波分解层数研究

首先根据小波变换原理,采用Db9小波基函数,对多组多光谱图像分别进行1～5层小波分解,然后根据小波逆变换原理对系数融合后的图像进行逆变换,得到不同小波分解层的融合图像.最后,利用图像质量评价方法信息熵、标准差、互信息、以及图像融合质量综合评价方法等,对不同分解层下的融合图像进行了评价.实验结果表明:小波变换在一层小波分解时,图像融合效果最佳.     

基于密集连接生成对抗网络的图像颜色迁移

针对传统颜色迁移算法在处理图像时存在颜色误传递,色彩不够自然等问题,提出一种基于密集连接生成对抗网络的图像颜色迁移方法。在训练过程中,训练生成网络生成颜色迁移图像。生成网络中的编码层利用密集连接网络跨层连接的优点促进颜色特征重用,加快网络的收敛速度,同时在转换层采用3层残差模块代替原始的两层残差模块更好地组合图像的不同特征。训练判别网络使其辨别原图像与生成的迁移图像间的差别。本文判别网络中用-log函数计算模型损失,加快训练初期更新速度。实验结果表明,与同类模型相比,本文方法结果图像保留更多细节,且能够抑制部分噪声,整体更接近自然图像。     

基于多级联递进卷积结构的图像去雨算法

雨天图像会影响计算机视觉任务的效果与精度。雨天图像常常包含来自不同方向、大小、形状的雨点或雨痕，在对这些雨点、雨痕进行去除时，现有的方法往往没有考虑到雨天图像不同精细尺度下的特征信息，仅采用单一尺度进行图像去雨存在很大缺陷，无法恢复出足够清晰的视觉任务图像。受益于卷积神经网络架构的强大特征提取能力，本文提出了一种端到端的多级联递进卷积结构算子，该算子包含4层卷积层，通过阶梯化连接构成一个整体模块，该模块可以针对多尺度场景下的雨天进行特征提取并整合。将该算子模块嵌入到渐进循环网络结构中，利用循环结构多次去除雨纹，最终有效还原出接近真实图像的无雨图像。该方法在现有的人工合成雨图数据集Rain100H、Rain100L、Rain800与自动驾驶领域合成雨图数据集BDD1000上进行了对比实验。实验结果表明，该算法在4个数据集上的PSNR值达到了30.70,37.91,27.63,35.74 dB,SSIM值达到了0.914,0.980,0.894,0.977。通过真实雨图数据集去雨结果的可视化展示，充分验证了本文方法在去雨任务上的有效性。     

一种基于混合变换的分层图像表示与编码

提出一种基于混合变换的分层图像编码算法，它将原始图像划分成包含不同结构特征的图像平面，如平滑边缘层和纹理层等等，然后采用不同的压缩算法对不同的图像层进行编码，从而达到对整幅图像最优编码的目的。本文实际上给出了一种新的编码框架，在这个框架内综合了不同的信号变换方式，将它们有机结合起来能够提供一种有效的图像表示方式。实验结果表明，与采用单一小波图像编码算法相比，本文算法能够获得更好的图像恢复质量。     

不同光照条件下遥感图像边缘检测方法研究

开展遥感图像边缘检测时，若不能考虑不同光照条件对遥感图像的影响，会影响图像边缘检测时的检测精度，为提升图像检测效果，提出不同光照条件下遥感图像边缘检测方法研究。该方法首先分析不同光照条件下遥感图像影响因素，并对图像实施畸变校正、去噪等处理；使用图像的融合技术对图像实施模糊化处理，实现图像的增强降低光照条件对图像检测的影响；最后通过Zernike边缘检测方法识别图像边缘点，完成图像的边缘检测。实验结果表明，本方法在开展遥感图像边缘检测时，平均梯度为0.133,信息熵为4.213,检测时间为1.352 s。     

基于引导滤波二尺度分解的红外与可见光图像融合

为了降低多尺度分解融合算法的复杂性，并提高融合图像适应人类视觉特点，本文提出一种基于引导滤波二尺度分解的红外与可见光图像融合的方法。首先利用引导滤波对可见光图像实施增强的图像预处理，然后利用引导滤波将源图像分解为基础层和细节层。在细节层的融合规则中我们采用能量保护和细节提取的方法，最后将融合后的细节层与基础层合成融合结果。实验结果表明所给方法在提高视觉感知、细节处理、边缘保护等方面都有良好的效果。本文最后还讨论了可见光图像增强对融合方法的影响：从实验数据可知，增强可以提升融合效果，但在图像融合中融合方法才是关键。     

基于引导滤波二尺度分解的红外与可见光图像融合

为了降低多尺度分解融合算法的复杂性，并提高融合图像适应人类视觉特点，本文提出一种基于引导滤波二尺度分解的红外与可见光图像融合的方法。首先利用引导滤波对可见光图像实施增强的图像预处理，然后利用引导滤波将源图像分解为基础层和细节层。在细节层的融合规则中我们采用能量保护和细节提取的方法，最后将融合后的细节层与基础层合成融合结果。实验结果表明所给方法在提高视觉感知、细节处理、边缘保护等方面都有良好的效果。本文最后还讨论了可见光图像增强对融合方法的影响：从实验数据可知，增强可以提升融合效果，但在图像融合中融合方法才是关键。     

基于深度学习算法的三维激光雷达主动成像目标检测

为了提升目标检测效果，设计基于深度学习算法的三维激光雷达主动成像目标检测方法。利用深度学习算法的生成对抗网络，剔除三维激光雷达主动成像过程中的杂波干扰，得到无杂波干扰的目标三维图像；设计生成模型与对抗模型的损失函数，利用端到端深度神经网络的点云编码层，在无杂波干扰的目标三维图像内，提取目标三维图像特征，并输入目标检测层内；通过目标检测层输出目标检测候选框，利用非极大值结合混合置信度，确定最终目标检测框，完成三维激光雷达主动成像目标检测。实验结果表明：该方法可有效剔除杂波干扰，得到无杂波干扰的目标三维图像；该方法可有效完成三维激光雷达主动成像目标检测，且在不同目标运动模糊长度像素时，该方法目标检测的交并比均高于阈值，说明该方法的目标检测精度较高。     

一种新的基于二尺度分解的图像和谐融合方法

介绍了一种新颖的图像融合算法。该方法首先将图像的亮度通道进行分解,然后对分 解后的层使用不同的方式进行处理。该方法使用均值插值法来解决图像融合问题。实验表明 ,该方法在外观不同的图像上能够获得比较满意的结果,融合结果和目标图像的细节纹理匹 配完好且无缝。此外,基于图形处理器（GPU）的并行实现提高了算法的效率。     

面向双模态红外图像差异的拟态融合方法

针对传统融合方法无法根据双模态红外图像差异特征的不同选择有效的融合策略的问题,提出了一种面向红外光强与偏振图像差异的拟态融合方法。首先计算图像特征差异度对差异特征进行粗筛,制定主差异特征类型的选取规则来确定图像组的主差异特征;然后构造特征融合度,以建立差异特征与拟态变元集中各层变元的映射,确定变元分层结构;最后在变元分层结构选择主差异特征类型的各层变元,比较不同拟态结构变元组合时差异特征的特征融合度,确定其最大值占比最高的拟态结构,形成变体。实验结果表明,经主观分析本文方法结果的视觉效果比对比方法结果的效果更优;经客观评价本文方法结果均为有效融合,因此本文方法实现了对融合策略的自适应选择并提高了图像的融合质量。     

基于差分隐私的权重社会网络隐私保护

针对权重社会网络发布隐私保护中的弱保护问题,提出一种基于差分隐私模型的随机扰动方法可实现边及边权重的强保护。设计了满足差分隐私的查询模型-WSQuery,WSQuery模型可捕获权重社会网络的结构,以有序三元组序列作为查询结果集;依据WSQuery模型设计了满足差分隐私的算法-WSPA,WSPA算法将查询结果集映射为一个实数向量,通过在向量中注入Laplace噪音实现隐私保护;针对WSPA算法误差较高的问题提出了改进算法-LWSPA,LWSPA算法对查询结果集中的三元组序列进行分割,对每个子序列构建满足差分隐私的算法,降低了误差,提高了数据效用。实验结果表明,提出的隐私保护方法在实现隐私信息的强保护同时使发布的权重社会网络仍具有可接受的数据效用。     

Image quality assessment based on adaptive multiple Skyline query

Non-reference image quality assessment has attracted great emphasis in recent years. Traditional image quality assessment algorithms based on structural similarity cannot make full use of the image gradient features, and the contrast similarity features often ignore the consistency of continuous color blocks within the image, which leads to large discrepancy between the evaluation result and the subjective judgment of human vision system. In this paper, we propose a deep model for image quality assessment where the spatial and visual features of image are both considered. For better feature fusion, we design an adaptive multiple Skyline query algorithm named MSFF, which takes as input multiple features of images, and learns the feature weights through end-to-end training. Extensive experiments on image quality assessment tasks prove that the proposed model exhibits superior performance compared with existing solutions.     

基于MapReduce的增广动态Skyline查询处理方法

Skyline查询能够计算大规模的数据集中满足多个标准的最优解,被广泛应用于多目标决策等领域.动态skyline查询作为skyline查询的一种重要变体,其结果随着查询点的不同而动态改变,为用户在指定查询要求方面提供了更大的灵活性.然而,随着数据量的不断增加,动态skyline查询会产生大量的查询结果,忽略了查询点的维度方向性和数据的全局整体性,给用户的选择带来极大困难.因此,需要进一步优化动态skyline查询的结果集,提高全局整体性,过滤冗余数据.针对上述问题,提出一种基于MapReduce的增广动态skyline查询处理方法.该方法将原始数据按照维度信息进行分区,在多个节点并行计算动态skyline,优化传统动态skyline结果集,同时提供全局更优的结果供用户选择.在此基础上,针对用户给出某些维度的容忍度的情况,提出一种引入用户容忍度的增广动态skyline查询处理方法.该方法可以根据用户容忍度缩减增广动态skyline查询的原始数据集,很大程度上减少中间结果的比较次数,并且提高了结果集的准确度.大量实验证明,基于MapReduce的增广动态skyline查询处理方法具有更好的有效性、准确性和可用性.     

Three Degree Binary Graph and Shortest Edge Clustering for re-ranking in multi-feature image retrieval

Graph methods have been widely employed in re-ranking for image retrieval. Although we can effectively find visually similar images through these methods, the ranking lists given by those approaches may contain some candidates which appear to be irrelevant to a query. Most of these candidates fall into two categories: (1) the irrelevant outliers located near to the query images in a graph; and (2) the images from another cluster which close to the query. Therefore, eliminating these two types of images from the ordered retrieval sets is expected to further boost the retrieval precision. In this paper, we build a Three Degree Binary Graph (TDBG) to eliminate the outliers and utilize a set-based greedy algorithm to reduce the influence of adjacent manifolds. Moreover, a multi-feature fusion method is proposed to enhance the retrieval performance further. Experimental results obtained on three public datasets demonstrate the superiority of the proposed approach.     

SS*:一种嵌入视觉特性的多维图像索引算法

图像检索因信息量巨大，查询速度至关重要。一种有效的方法是对图像特征进行多维索引，然后按多维索引算法检索。但是，现有的多维索引算法并不是专门针对图像数据库设计的，没有考虑图像的视觉特性，检索性能不理想。文章针对图像信息的特点，结合SS多维索引算法，设计了一种新的基于内容的图像检索的多维索引算法——SS^*算法。实验表明，该算法对图像检索是有效的。     

Real-world image dehazing with improved joint enhancement and exposure fusion

In this work, a single image dehazing method that improves the haze removal capacity of the Joint Contrast Enhancement and Exposure Fusion (CEEF) method with Smoothing-Sharpening Image Filter (SSIF) is presented. In this method, the hazy image is first sharpened with SSIF to obtain a sharper image. In this way, the difference between haze and objects is amplified. Then, the AHE procedure in CEEF is replaced by CLAHE to obtain an enhanced CEEF. The enhanced CEEF is applied to the filtering result to obtain the final dehazed image. Observations demonstrate that the proposed method obtains enhanced results while reducing the amount of haze. The visual and quantitative comparisons between the proposed method and state-of-the-art dehazing methods show that the proposed method has better dehazing performance and has a 50% improvement in terms of the FADE metric compared to the closest result.     

Online image search result grouping with MapReduce-based image clustering and graph construction for large-scale photos

Current image search system uses paged image list to show search results. However, the problems such as query ambiguity make users hard to find search targets in such image list. In this work, we propose an image search result grouping system that summarizes image search results in semantic and visual groups. We use MapReduce-based image graph construction and image clustering methods to deal with scalability problem on this system. By precomputing image graphs and image clusters at offline stage, this system can be efficient at responding user query. The experiments on two large scale Flickr image datasets are conducted for our system. Compared with using single machine, our graph construction method is 69 times faster. We conduct a comprehensive user study to compare our approach with state-of-the-art baseline methods. We find that our approach generates competent image groups with a 2–100 times speeded-up.     

Relevance feedback using generalized Bayesian framework with region-based optimization learning.

This paper presents a generalized Bayesian framework for relevance feedback in content-based image retrieval. The proposed feedback technique is based on the Bayesian learning method and incorporates a time-varying user model into the formulation. We define the user model with two terms: a target query and a user conception. The target query is aimed to learn the common features from relevant images so as to specify the user's ideal query. The user conception is aimed to learn a parameter set to determine the time-varying matching criterion. Therefore, at each feedback step, the learning process updates not only the target distribution, but also the target query and the matching criterion. In addition, another objective of this paper is to conduct the relevance feedback on images represented in region level. We formulate the matching criterion using a weighting scheme and proposed a region clustering technique to determine the region correspondence between relevant images. With the proposed region clustering technique, we derive a representation in region level to characterize the target query. Experiments demonstrate that the proposed method combined with time-varying user model indeed achieves satisfactory results and our proposed region-based techniques further improve the retrieval accuracy.     

Geo-localization based on CNN feature matching

A geo-localization method is proposed for military and civilian applications, which is used when no global navigation satellite system (GNSS) information is available. The open graphics library (OpenGL) is used to build a three-dimensional geographic model of the test area using digital elevation model (DEM) data, and the skyline can thus be extracted with the model to form a database. Then, MultiSkip DeepLab (MS-DeepLab), a fully convolutional semantic segmentation network with multiple skip structures, is proposed to extract the skyline from the query image. Finally, a matching model based on convolutional neural network (CNN) feature is adopted to calculate the similarity between the skyline features of the query image and the DEM database to realize automatic geo-localization. The experiments are conducted at a 202.6 km2 test site in north-eastern Changsha, China. 50 test points are selected to verify the effectiveness of the proposed method, and an excellent result with an average positioning error of 49.29 m is obtained.     

基于统计机器翻译模型的查询扩展

在搜索引擎等实际的信息检索应用中,用户提交的查询请求通常都只包含很少的几个关键词,这会引起相关文档与用户查询之间的词不匹配问题,对检索性能有较严重的负面影响。该文在分析了查询产生模型的基础上,提出了一种新的基于统计机器翻译的查询扩展方法。通过统计机器翻译模型提取文档集中与查询词相关联的词,用以进行查询扩展。在TREC数据集上的试验结果表明:基于统计翻译的查询扩展方法不仅比不扩展的语言模型方法始终有12%～17%的提高,而且比流行的查询扩展方法-伪反馈也具有可比的平均准确率。