A 360-Degree Panoramic Image Inpainting Network Using a Cube Map

Inpainting has been continuously studied in the field of computer vision. As artificial intelligence technology developed, deep learning technology was introduced in inpainting research, helping to improve performance. Currently, the input target of an inpainting algorithm using deep learning has been studied from a single image to a video. However, deep learning-based inpainting technology for panoramic images has not been actively studied. We propose a 360-degree panoramic image inpainting method using generative adversarial networks (GANs). The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format, which has relatively little distortion and uses it as a training network. Since the cube map format is used, the correlation of the six sides of the cube map should be considered. Therefore, all faces of the cube map are used as input for the whole discriminative network, and each face of the cube map is used as input for the slice discriminative network to determine the authenticity of the generated image. The proposed network performed qualitatively better than existing single-image inpainting algorithms and baseline algorithms.     

Hydrogen sensing by RGB investigation of gasochromic coloration of MoO3/Pd-coated polyester fabrics

Recently, colorimetric sensors capable of detecting explosive and toxic molecules have attracted much attention for applications in health and environmental monitoring. Here, we demonstrate the detection of hydrogen gas using gasochromic fabrics and evaluate their performance with a commercial RGB color sensor module. For this purpose, first a thin Pd film was sputter deposited onto the polyester fabric and then amorphous MoO₃ films (several microns) were deposited by RF reactive magnetrons in various O₂/Ar ratios (from 2.5 to 12.5 O₂). Field emission scanning electron microscope (FESEM) identified the morphological changes of the surface at each coating step and showed that the fibrous structure of the fabrics was preserved after coating of the films, which is suitable for better gas adsorption. Exposure to hydrogen caused the obtained MoO₃/Pd/polyester samples to turn blue-gray at room temperature and the UV–Vis spectra showed an increase in optical absorption. Their sensitivity was evaluated in the presence of different H₂ concentrations from 250 to 10,000 ppm by recording the time variation of color difference (RGB Euclidean distance). A significant correlation was found between absorption spectrum and RGB analysis with respect to oxygen content. The color variation showed a linear behavior with respect to hydrogen concentration for all samples. Response and recovery times, reversibility and reproducibility in the presence of hydrogen gas were also evaluated using the RGB readout data. Overall, the RGB module optimally depicts the sensing characteristics of the gasochromic fabrics in terms of reversibility, sensitivity and reproducibility, which may contribute to their commercial development.     

Soft sensing of water depth in combined sewers using LSTM neural networks with missing observations

Information and communication technologies combined with in-situ sensors are increasingly being used in the management of urban drainage systems. The large amount of data collected in these systems can be used to train a data-driven soft sensor, which can supplement the physical sensor. Artificial Neural Networks have long been used for time series forecasting given their ability to recognize patterns in the data. Long Short-Term Memory (LSTM) neural networks are equipped with memory gates to help them learn time dependencies in a data series and have been proven to outperform other type of networks in predicting water levels in urban drainage systems. When used for soft sensing, neural networks typically receive antecedent observations as input, as these are good predictors of the current value. However, the antecedent observations may be missing due to transmission errors or deemed anomalous due to errors that are not easily explained. This study quantifies and compares the predictive accuracy of LSTM networks in scenarios of limited or missing antecedent observations. We applied these scenarios to an 11-month observation series from a combined sewer overflow chamber in Copenhagen, Denmark. We observed that i) LSTM predictions generally displayed large variability across training runs, which may be reduced by improving the selection of hyperparameters (non-trainable parameters); ii) when the most recent observations were known, adding information on the past did not improve the prediction accuracy; iii) when gaps were introduced in the antecedent water depth observations, LSTM networks were capable of compensating for the missing information with the other available input features (time of the day and rainfall intensity); iv) LSTM networks trained without antecedent water depth observations yielded larger prediction errors, but still comparable with other scenarios and captured both dry and wet weather behaviors. Therefore, we concluded that LSTM neural network may be trained to act as soft sensors in urban drainage systems even when observations from the physical sensors are missing.     

用于发光温度传感的金属有机框架材料

金属有机框架(Metal organic frameworks,MOFs)由于其显著的结构多样性和可调的发光性能,为制备不同种类的发光传感器提供了良好契机。近年来,利用发光MOFs探测温度传感技术受到了人们的广泛关注。结合对发光测温的描述后,总结了发光型MOF温度计的最新研究进展,重点介绍了双发射型MOF在温度传感领域中的广泛应用。     

基于改进网格运动统计特征的图像匹配算法

为了解决尺度不变特征变换（SIFT）算法在图像匹配中匹配正确率低、耗时长等问题，提出一种基于改进网格运动统计特征RANSAC-GMS的图像匹配算法。首先，利用快速旋转不变性特征（ORB）算法对图像进行预匹配，对预匹配的特征点采用网格运动统计（GMS）来支持估计量以实现正确匹配点与错误匹配点的区分；然后，采用改进的随机抽样一致性（RANSAC）算法通过匹配点间的距离相似性对特征点进行筛选，并采用评价函数对筛选后的新数据集进行重新整理，进而实现对误匹配点的剔除。采用Oxford标准图库和现实中拍摄的图像对图像匹配算法进行测试对比，实验结果表明，所提算法在图像匹配中的平均匹配正确率达到91%以上；与GMS、SIFT、ORB等算法相比，该改进算法的近景匹配正确率和远景匹配正确率分别最少提高了16.15个百分点和3.56个百分点，说明它能有效剔除误匹配点，进一步提高图像匹配精度。     

基于Simhash的安全密文排序检索方案

针对密文检索中存在的计算量大、检索效率不高的问题，提出一种基于Simhash的安全密文排序检索方案。该方案基于Simhash的降维思想构建安全多关键词密文排序检索索引（SMRI），将文档处理成指纹和向量，利用分段指纹和加密向量构建B+树，并采用"过滤-精化"策略进行检索和排序，首先通过分段指纹的匹配进行快速检索，得到候选结果集；然后通过计算候选结果集与查询陷门的汉明距离和向量内积进行排序，带密钥的Simhash算法和安全k近邻（SkNN）算法保证了检索过程的安全性。实验结果表明，与基于向量空间模型（VSM）的方案相比，基于SMRI的排序检索方案计算量小，能节约时间和空间成本，检索效率高，适用于海量加密数据的快速安全检索。     

基于流形学习的光学遥感图像分类

随着光学遥感图像技术的快速发展与广泛应用,对光学遥感图像的准确分类具有深远的研究意义。传统特征提取方式提取的高维特征中夹杂着许多冗余信息,分类过程可能导致过拟合现象,针对传统的线性降维算法不足以保持原始数据的内部结构,容易造成数据失真这一问题,提出基于流形学习的光学遥感图像分类算法。该算法首先提取出图像的SIFT特征,然后将流形学习运用于特征降维,最后结合支持向量机进行训练和识别。实验结果表明,在Satellite、NWPU和UCMerced实验数据中,冰川、建筑群和海滩分类精度得到了有效提高,达到85%左右;针对沙漠、岩石、水域等特殊环境遥感图像,分类精度提高了10%左右。总而言之,基于流形学习的分类算法对通过降维之后的数据能够保持在原高维空间中的拓扑结构,相似特征点能得到有效聚合,预防了"维数灾难",减少了计算量,保证了分类精度。     

Docker容器化下的遥感算法程序集成方法

目的 近年来，随着我国遥感技术的快速发展，遥感数据呈现出大数据的特点，遥感数据的时效性增强，针对新环境下遥感算法编程语言众多，程序运行和部署环境需求多样，程序的集成和部署困难的问题，提出了一种遥感算法程序快速封装与Docker容器化系统集成架构。方法 该系统架构主要包括：1）遥感算法程序的镜像自动化封装制作；2）镜像的分发管理，达到算法程序镜像的共享；3）遥感信息产品生产流程的容器化编排服务，将相关联的算法程序镜像串联，以满足特定遥感信息产品的生产；4）容器的调度运行，调用镜像，实现特定遥感产品的容器化运行。本文在上述容器化系统集成架构下，以Landsat5数据的NDVI、NDWI信息产品的生产作为容器化生产实例，并同物理机、KVM （kernel-based virtual machine）虚拟机在运行时间、内存占用量、部署效率等性能进行了对比。结果 Docker容器虚拟化环境下的产品生产和物理机环境下在运行时间和内存占用量上几无差别，优于KVM虚拟机。Docker容器虚拟化环境和KVM虚拟机环境下在部署上能够节省大量时间，相比于物理机环境能够提高部署效率。结论 容器化的系统集成方式能够有效解决遥感算法程序集成和部署困难的问题，有利于遥感算法程序的复用和流程的共享，提高系统集成效率，具备较强的遥感数据实时快速处理能力。     

中国散裂中子源靶体研制

中国散裂中子源(CSNS)靶体选用钨为靶材、钽为包覆层，采用包套法结合热等静压扩散焊工艺制备了钽包覆钨靶片。经检测，钨钽界面结合良好，钽层与钨基体平均结合强度大于64.07 MPa。靶体将钨靶片分成厚度不等的11片，散热采用一进一出的并行流结构，利用CFD软件进行了模拟计算，钨靶片间冷却流道间隙为1.2 mm，100 kW满功率运行情况下靶体最高温度为182.3 ℃，冷却水温升为7.1 ℃。经过半年多的试运行，CSNS靶体各参数满足CSNS的要求。     

Controllable Image‐Based Transfer of Flow Phenomena

Modelling flow phenomena and their related weathering effects is often cumbersome due their dependence on the environment, materials and geometric properties of objects in the scene. Example‐based modelling provides many advantages for reproducing real textures, but little effort has been devoted to reproducing and transferring complex phenomena. In order to produce realistic flow effects, it is possible to take advantage of the widespread availability of flow images on the Internet, which can be used to gather key information about the flow. In this paper, we present a technique that allows the transfer of flow phenomena between photographs, adapting the flow to the target image and giving the user flexibility and control through specifically tailored parameters. This is done through two types of control curves: a fitted theoretical curve to control the mass of deposited material, and an extended colour map for properly adapting to the target appearance. In addition, our method filters and warps the input flow in order to account for the geometric details of the target surface. This leads to a fast and intuitive approach to easily transfer phenomena between images, providing a set of simple and intuitive parameters to control the process.