ID	原文	译文
953	针对云存储系统中的数据安全问题，提出了一种面向云存储安全的可自愈拜占庭 Quorum 系统。	For the problem of data security in the cloud storage system, a self-healing Byzantine Quorum system forthe cloud storage security is proposed.
954	该系统以虚拟机作为后端存储设备构建虚拟存储节点，利用虚拟机多样化操作系统，以及动态迁移、快速部署等机制构建动态异构的存储系统架构。	In this system, the virtual machines are used as back-end storage devices to constructthe virtual storage node. The diverse operating systems, dynamic migration and rapid generation mechanism of virtual ma-chines are introduced to build dynamic and heterogeneous storage system architecture.
955	在拜占庭容错门限的基础上，提出自愈门限的概念，并设计相应系统安全协议，实现存储节点的自动化异常检测和状态复原。	On the basis of the Byzantine fault tol-erance threshold, the concept of self-healing threshold is presented and several security protocols are devised to achieve auto-mated anomaly detection and storage node recovery.
956	实验结果表明，提出的云存储系统具有较高的鲁棒性，能有效提高存储数据的安全性。	The experimental results show that the proposed cloud storage system isgreatly robust and can effectively improve the security of stored data.
957	针对现有场景流计算方法在复杂场景、大位移和运动遮挡等情况下易产生运动边缘模糊的问题，提出一种基于语义分割的双目场景流估计方法。	In order to address the issue of motion boundary blurring caused by the complex scenes, large displacementand motion occlusion, this paper proposes a binocular scene flow estimation method based on semantic segmentation.
958	首先，根据图像中的语义信息类别，通过深度学习的卷积神经网络模型将图像划分为带有语义标签的区域;	Firstly, by using the image semantic information, we classify the image regions into several categories with semantic labels through convolutional neural networks.
959	针对不同语义类别的图像区域分别进行运动建模，利用语义知识计算光流信息并通过双目立体匹配的半全局匹配方法计算图像视差信息。	Then we plan the motion models of various image regions according to the different semantic categories and compute the optical flow and disparity under the prior knowledge of semantic information.
960	然后，对输入图像进行超像素分割，通过最小二乘法耦合光流和视差信息，分别求解每个超像素块的运动参数。	Secondly, we apply the superpixel segmentation to the input image and couple the optical flow and disparity information via least squares methodto solve the motion parameters of each superpixel patch.
961	最后，在优化能量函数中添加语义分割边界的约束信息，通过更新像素到超像素块的映射关系和超像素块到移动平面的映射关系得到最终的场景流估计结果。	Finally, we add the boundary information of semantic segmentation constraint to the optimization energy function, and estimate the scene flow by updating the mappings of pixels-to-superpixel and superpixel-to-plane.
962	采用 KITTI 2015 标准测试图像序列对本文方法和代表性的场景流计算方法进行对比分析。	We evaluate the proposed approach and some state-of-the-art methods on the KITTI 2015 database to conduct a comparison experiment.