Decomposition and replacement: Spatial knowledge distillation for monocular depth estimation

Knowledge distillation has become a key technique for making smart and light-weight networks through model compression and transfer learning. Unlike previous methods that applied knowledge distillation to the classification task, we propose to exploit the decomposition-and-replacement based distillation scheme for depth estimation from a single RGB color image. To do this, Laplacian pyramid-based knowledge distillation is firstly presented in this paper. The key idea of the proposed method is to transfer the rich knowledge of the scene depth, which is well encoded through the teacher network, to the student network in a structured way by decomposing it into the global context and local details. This is fairly desirable for the student network to restore the depth layout more accurately with limited resources. Moreover, we also propose a new guidance concept for knowledge distillation, so-called ReplaceBlock, which replaces blocks randomly selected in the decoded feature of the student network with those of the teacher network. Our ReplaceBlock gives a smoothing effect in learning the feature distribution of the teacher network by considering the spatial contiguity in the feature space. This process is also helpful to clearly restore the depth layout without the significant computational cost. Based on various experimental results on benchmark datasets, the effectiveness of our distillation scheme for monocular depth estimation is demonstrated in details. The code and model are publicly available at : https://github.com/tjqansthd/Lap_Rep_KD_Depth.     

改进RetinaFace的自然场景口罩佩戴检测算法

新型冠状病毒可以通过空气中的飞沫、气溶胶等载体进行传播，在公共场所下正确佩戴口罩可以有效地防止病毒的传播。提出了一种自然场景下人脸口罩佩戴检测方法，对RetinaFace算法进行了改进，增加了人脸口罩佩戴检测任务，优化了损失函数。在特征金字塔网络中引入了一种改进的自注意力机制，增强了特征图的表达能力。建立了包含3 000张图片的数据集，并进行手工标注，用于网络训练。实验结果表明该算法可以有效进行口罩佩戴检测，在自然场景视频中也取得了不错的检测效果。     

基于双重金字塔网络的视频目标分割方法

针对复杂视频场景中难以分割特定目标的问题，提出一种基于双重金字塔网络（DPN）的视频目标分割方法。首先，通过调制网络的单向传递让分割模型适应特定目标的外观。具体而言，从给定目标的视觉和空间信息中学习一种调制器，并通过调制器调节分割网络的中间层以适应特定目标的外观变化。然后，通过基于不同区域的上下文聚合的方法，在分割网络的最后一层中聚合全局上下文信息。最后，通过横向连接的自左而右结构，在所有尺度中构建高阶语义特征图。所提出的视频目标分割方法是一个可以端到端训练的分割网络。大量实验结果表明，所提方法在DAVIS2016数据集上的性能与较先进的使用在线微调的方法相比，可达到相竞争的结果，且在DAVIS2017数据集上性能较优。     

A Novel Method of Heart Failure Prediction Based on DPCNNXGBOOST Model

The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients. Existing methods depend on the judgment of doctors, the results are affected by many factors such as doctors’ knowledge and experience. The accuracy is difficult to guarantee and has a serious lag. In this paper, a mixture prediction model is proposed for perioperative adverse events of heart failure, which combined with the advantages of the Deep Pyramid Convolutional Neural Networks (DPCNN) and Extreme Gradient Boosting (XGBOOST). The DPCNN was used to automatically extract features from patient’s diagnostic texts, and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients, then the XGBOOST algorithm was used to construct the prediction model of heart failure. An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018. The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3% and 31% compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.     

用VSP资料实现声测井与地面地震资料的匹配

在分析声测井与地面地震资料的差异以及回顾多分辨率分析理论的基础上，试验了在ＶＳＰ资料的约束下，用多分辨率分析方法改善声测井与地面地震资料的匹配问题，理论模型和野外实测数据表明，ＶＳＰ资料提供的直接深时关系是实现声测井与地面地震资料正确标定的宝贵资料；多分辨率分析方法与直接抽取、多眯平均及中值滤波等方法相比，能使声测井与地震资料得到更好地匹配。     

基于多尺度纹理特征的EPR电缆终端故障诊断方法

高速铁路列车中乙丙橡胶(EPR)电缆终端常因制作过程中操作不当而导致出现多种缺陷,造成终端局部放电甚至击穿的现象,对检测到的局部放电信号进行准确分类仍然是亟待解决的难题。分别制作了含尖端、环切划伤、金属微粒、气隙4种典型缺陷的终端试样,通过试验记录了各类试样的放电谱图信息。基于试验得到的局部放电谱图库,提出通过图像金字塔理论,构建多尺度局部放电谱图空间,并从中提取1阶纹理统计量、2阶纹理统计量及高阶纹理统计量作为缺陷类型识别的特征参量。同时,结合随机森林算法,基于gini指数完成了特征空间寻优工作,实现了对缺陷类型的正确分类。结果表明：通过随机森林算法,多尺度纹理特征的模型误差率和分类准确率明显优于单尺度纹理特征,能较好地对终端典型缺陷进行分类;同时,由于气隙缺陷和划伤缺陷的放电机理存在相似性,二者缺陷处的局部放电特征同样存在相似现象,因此气隙缺陷和划伤缺陷的分类较易出现误差,导致其识别率偏低,还需针对其图像特征参数和识别算法继续开展研究。     

基于云平台Hadoop的三维虚拟地球数据组织形式

云计算的发展推动了整个行业的进步,同时也给GIS的发展提供了非常大的机会。本文针对开源云平台Hadoop搭建了一个小型的私有云,利用Hadoop HBase存储键值对数据的优势,将三维虚拟地球GeoGlobe格式数据存储于HBase之上,实现了三维GIS的金字塔状瓦片数据存储到HBase中,最后给出了具体的实现方案。     

数字压缩技术在改善空问数据网络传输的研究

从当前WebGIS的应用系统结构出发,根据地图瓦片技术应用的特点,从数据压缩和网络传输技术两方面来考虑如何通过减少数据量来提高用户体验,其中前者主要通过剔除PNG文件冗余数据信息,经过无损压缩减少数据本身数据量。而后者则通过GZIP压缩技术,实现在矢量块数据传输之前,对数据先进行动态压缩,再通过网络传输到达目的端后自动解压缩的方法,从而有效减少了网络传输中的数据量,节省了数据传输时间。实验及应用表明,以上两种方法能实际应用中极较好地改善数据传输性能,提高用户体验。     

基于颜色四通道及空间金字塔的鱼类图像检索

随着计算机视觉技术在海洋水产领域中的应用不断加深，鱼类图像检索在渔业资源调查、鱼类行为学分析等方面发挥了巨大的作用。通过研究发现，鱼类图像的背景信息会对鱼类图像检索造成极大干扰，而且鱼类图像中颜色、纹理、形状等特征由于空间位置信息的缺乏而使检索的准确率不高。为解决以上问题，提出了一种新的基于颜色四通道及空间金字塔的鱼类图像检索算法。首先，提取视觉显著性图将鱼类图像的前景和背景分开，从而减少图像背景对检索的干扰；其次，为了使图像特征包含一定的空间位置信息，利用空间金字塔的理论对图像进行分割，在此基础上，将图像转为HSVG四通道图并提取SURF特征；；最后，得到检索结果。为验证所提算法的有效性，在QUT_fish_data数据集和DLOU_fish_data数据集上对算法的查全率、查准率与经典的HSVG算法和显著性分块算法进行对比：在两个数据集上查准率分别比传统的HSVG算法最多分别提高12%和5%，查全率最多分别提高7%和22%；比传统的显著性分块算法查准率最多分别提高15%和5%，查全率最多分别提高36%和22%；从而证明所提算法是有效的，能有效提升鱼类图像的检索效果。     

Total and selective reuse of Krylov subspaces for the resolution of sequences of nonlinear structural problems

This paper deals with the definition and optimization of augmentation spaces for faster convergence of the conjugate gradient method in the resolution of sequences of linear systems. Using advanced convergence results from the literature, we present a procedure on the basis of a selection of relevant approximations of the eigenspaces for extracting, selecting and reusing information from the Krylov subspaces generated by previous solutions in order to accelerate the current iteration. Assessments of the method are proposed in the cases of both linear and nonlinear structural problems. Copyright © 2012 John Wiley & Sons, Ltd.