An automatic 2D to 3D video conversion approach based on RGB-D images

3D movies/videos have become increasingly popular in the market; however, they are usually produced by professionals. This paper presents a new technique for the automatic conversion of 2D to 3D video based on RGB-D sensors, which can be easily conducted by ordinary users. To generate a 3D image, one approach is to combine the original 2D color image and its corresponding depth map together to perform depth image-based rendering (DIBR). An RGB-D sensor is one of the inexpensive ways to capture an image and its corresponding depth map. The quality of the depth map and the DIBR algorithm are crucial to this process. Our approach is twofold. First, the depth maps captured directly by RGB-D sensors are generally of poor quality because there are many regions missing depth information, especially near the edges of objects. This paper proposes a new RGB-D sensor based depth map inpainting method that divides the regions with missing depths into interior holes and border holes. Different schemes are used to inpaint the different types of holes. Second, an improved hole filling approach for DIBR is proposed to synthesize the 3D images by using the corresponding color images and the inpainted depth maps. Extensive experiments were conducted on different evaluation datasets. The results show the effectiveness of our method.

     

An augmented reality-based multimedia environment for experimental education

Over the last few years, there has been a growing interest in augmented reality (AR) technology for education. However, current AR education applications are often used as a new type of knowledge display platform, and they cannot fully participate in educational activities to improve educational results. To enable AR technology to participate in educational activities more effectively, according to learning-by-doing theory, we explore the form of a future experimental course and propose a new AR-based multimedia environment for experimental education. The framework of the multimedia environment consists of three components: the AR experiment authoring tool, the AR experiment application, and the management application. In this AR-based multimedia environment, teachers can independently create AR experiments using the what you see is what you get (WYSIWYG) editing method. Students can manipulate the AR-based experimental object to complete the experiment in class. Moreover, teachers can observe students’ experimental behaviour, obtain evaluations in real time, and even guide students remotely. We also present an application case of a chemistry experiment and obtain results of the usability test, demonstrating improvements in AR technology participation in educational activities.

     

Robust person re-identification via graph convolution networks

Person re-identification (re-id) aims to identity the same person over multiple cameras; it has been successfully applied to various computer vision applications as a fundamental method. Owing to the development of deep learning, person re-id methods, which typically use triplet networks based on triplet loss, have demonstrated great success. However, the appearances of people are similar and hence difficult to distinguish in many cases. Therefore, we present a novel graph convolution network and enhances traditional triplet loss functions. Our method defines reference, positive, and negative features for triplet loss as three vertices of a graph, respectively, and adjusts their mutual distance through learning. The method adopts graph convolutions efficiently, thereby affording low computational costs. Experimental results demonstrate that our method is superior to the baseline on the Market-1501 dataset. The proposed GCN-based triplet loss considerably contributes to improve re-identification methods quantitatively and qualitatively.

     

空气质量细粒度数据内联关系可视分析系统

随着数据观测和数字计算技术的快速发展,空气质量数据粒度越来越细致,为研究空气质量的细粒度数据内联关系可视化、辅助理解空气污染物的转化规律提供了数据基础.针对蕴含丰富内联特征的大气质量细粒度数据开发了一个内联关系可视分析系统.首先,基于大气质量数据多维属性设计时空数据维度模型增强数据的时空表达,并提出一种基于深度学习的特征提取方法,将空气质量数据从高维空间映射到支持交互可视分析的低维特征空间;然后,设计了一套多视图联动的可视化系统,帮助用户发现空气污染传输中的细粒度内联关系,理解污染传输途径的数据分布特征.用户实例和用户评价结果表明,该系统是有效的.     

变压吸附控制在和利时MACS-K中的应用

本文以某公司甲醇合成装置PSA单元为对象,简要介绍变压吸附提氢控制在和利时MACS-K系列DCS中的实现方法及调试.     

基于生成对抗网络的多聚焦图像融合

多聚焦图像融合能够融合同一场景下具有不同聚焦部分的一系列图像.为了克服多聚焦图像融合模糊特征提取中存在的不足,提出一种基于U-Net的生成对抗网络模型.首先,生成器采用U-Net和SSE对多聚焦图像的特征进行提取,并完成图像融合;其次,判别器采用卷积层对已知的融合结果和生成器生成的融合图像进行分辨;然后,损失函数采用生成器的对抗损失、映射损失、梯度损失、均方误差损失和判别器对抗损失对生成网络进行参数调节;最后,将生成器、判别器和损失函数组成生成对抗网络模型,并进行实验.Pascal VOC2012数据集作为生成对抗网络的训练集,包括近焦图像、远焦图像、映射图像和融合图像.实验结果证明,该生成对抗网络模型能够有效地提取多聚焦图像中的模糊特征,且融合图像在互信息、相位一致性和感知相似性等方面表现优异.     

高校智能咨询系统实施过程中的关键问题研究

高校是"最多跑一次"思想的有力支持者,目前已有百余所高校同步推进,且取得显著成效.在此背景下,从高校留学生群体入手,分析当前高校智能咨询系统在"最多跑一次"实施落地过程中存在的问题.通过加强团队建设、规范事项、梳理流程、细化颗粒度的方式弥补仅靠系统带来的不足,旨在更好的为高校"最多跑一次"服务.     

复杂设备分级管理系统的设计与实现

为解决油田复杂设备管理效率低下的问题,基于分级管理思想,结合HTML、MySQL数据库和PHP技术,设计并实现了设备分级管理系统,并通过分级赋权等功能,提高了设备管理效率,实现了管理资源优化,使分级管理系统具有良好的推广前景。     

一种辅助新型冠状病毒肺炎检测的肺实质分割算法

新型冠状病毒肺炎给人类健康及社会经济造成了巨大的负面影响,而X光胸片中的肺实质提取成为新型冠状病毒肺炎诊断过程中的关键环节。在U-Net的基础上,提出一种结合编解码模式的肺实质分割算法。应用特征融合思想,构建A形特征融合模块,充分学习深层特征的语义信息。引入注意力机制,在深层卷积神经网络中加入密集空洞卷积模块和残差多核池化模块,扩大卷积感受野并提取上下文特征信息。通过改进可变形卷积和分割损失函数,提升网络模型的泛化能力和鲁棒性。实验结果表明,该算法的分割准确度、Dice系数、敏感度、Jaccard指数分别为98.16%、98.32%、98.13%、98.54%,能够实现X光胸片中肺实质部位的有效分割。     

基于持久性内存的单向移动B^+树

由新型非易失存储介质构成的持久性内存(persistent memory,PM)具有扩展性强、按字节访问与静态能耗低等特性,为未来主存与辅存融合提供了强大的契机.然而由于LLC(last level cache)具有易失性且与主存交互粒度通常为64B,而PM的原子持久化操作粒度为8B.因此,数据从LLC更新到PM的过程中,若发生故障,则可能破坏更新操作的失败原子性,进而影响原始数据的完整性.为了保证更新操作的失败原子性,目前研究主要采用显式调用持久化指令与内存屏障指令,将数据有序地持久化到PM上,但该操作会造成显著的开销,在索引更新中尤为明显.在对索引进行更新时,往往会涉及到索引结构的变化,该变化需要大量的有序持久化开销.研究旨在减少基于PM的B+树在更新过程中为保证失败原子性而引入的持久化开销.通过分析B+树节点利用率、不同更新模式下持久化开销以及更新操作之间的关系,提出了一种基于节点内数据真实分布的数据单向移动算法.通过原地删除的方式,减少删除带来的持久化开销.利用删除操作在节点内留下的空位,减少后续插入操作造成的数据移动,进而减少数据持久化开销.基于上述算法,对B+树的重均衡操作进行优化.最后通过实验证明,相较于最新基于PM的B+树,提出的单向移动B+树能够显著提高单一负载与混合负载性能.