摘要：【中文】本发明实施例提供一种图像控制方法及电子设备，涉及通信技术领域，以解决现有的电子设备显示的AR图像比较混乱，导致电子设备显示AR图像的方式不够灵活的问题。该方法包括：接收用户对N个对象中的目标对象的第一输入，N个对象中的每个对象分别对应至少一个AR图像，N个对象对应的AR图像均为与电子设备采集的实景图像对应的AR图像；响应于第一输入，显示或取消显示与目标对象对应的至少一个目标AR图像。该方法应用于电子设备显示AR图像的场景中。 【EN】The embodiment of the invention provides an image control method and electronic equipment, relates to the technical field of communication, and aims to solve the problem that the AR image displayed by the conventional electronic equipment is relatively disordered, so that the AR image display mode of the electronic equipment is not flexible enough. The method comprises the following steps: receiving first input of a user on a target object in N objects, wherein each object in the N objects corresponds to at least one AR image, and the AR images corresponding to the N objects are all AR images corresponding to live-action images collected by electronic equipment; in response to the first input, at least one target AR image corresponding to the target object is displayed or de-displayed. The method is applied to the scene of the electronic equipment displaying the AR image.

摘要：【中文】本发明公开了一种基于自编码观测器的卫星敏感器故障检测定位方法，该方法基于自编码观测器对卫星姿态敏感器进行故障检测定位，包括基于自编码器的观测器设计、支持向量机系统，根据卫星姿态测量方法搭建自编码观测器，比较观测器的输入和输出生成残差，用支持向量机根据残差的均值、均方差和信息熵对故障进行检测，组合多个自编码观测器的检测结果对故障传感器进行定位。本发明可以结合多个卫星姿态敏感器信号进行故障检测和故障定位，提高了卫星姿态控制系统的可靠性和地面监测能力。 【EN】The invention discloses a satellite sensor fault detection and positioning method based on a self-coding observer, which is used for carrying out fault detection and positioning on a satellite attitude sensor based on the self-coding observer and comprises observer design based on a self-encoder and a support vector machine system. The invention can combine a plurality of satellite attitude sensor signals to carry out fault detection and fault positioning, thereby improving the reliability and the ground monitoring capability of the satellite attitude control system.

摘要：【中文】本发明属于真空设备技术领域，具体公开了一种真空环境除湿排水系统，包括真空箱及与所述真空箱连接的除湿排水线路，除湿排水线路连接有储液容器，除湿排水线路包括排水线路和除湿线路，排水线路上设置有积水阀，除湿线路上设有冷却装置，储液容器还连接有泄放管路，泄放管路上设置有排水阀，积水阀与排水阀分时开启。采用本技术方案，通过排水线路排出真空箱内的积水，同时利用除湿线路去除真空环境内的水汽，确保真空设备的真空度。 【EN】The invention belongs to the technical field of vacuum equipment, and particularly discloses a vacuum environment dehumidification drainage system which comprises a vacuum box and a dehumidification drainage line connected with the vacuum box, wherein the dehumidification drainage line is connected with a liquid storage container, the dehumidification drainage line comprises a drainage line and a dehumidification line, a water accumulation valve is arranged on the drainage line, a cooling device is arranged on the dehumidification line, the liquid storage container is also connected with a discharge pipeline, a drain valve is arranged on the discharge pipeline, and the water accumulation valve and the drain valve are opened in a time-sharing manner. By adopting the technical scheme, accumulated water in the vacuum box is discharged through the drainage circuit, and water vapor in the vacuum environment is removed by utilizing the dehumidification circuit, so that the vacuum degree of the vacuum equipment is ensured.

摘要：【中文】本发明属于压裂返排液处理技术领域，公开了一种页岩气开采的压裂返排液的深度处理方法，所述深度处理系统包括：视频监控模块、参数监测模块、主控模块、预处理模块、电化学氧化处理模块、沉淀过滤模块、蒸发浓缩模块、分析模块、供电模块、显示模块。本发明通过参数监测模块可直接测定和计算各层段的压裂返排液量、每层段的压裂返排液中压裂液和地层水的比例等参数，还可以得到每层段的压裂返排液剖面；所判断的压裂情况直观准确，能够定量分析，且误差小，对同层段的压裂工作有重要的指导作用；同时，通过分析模块根据检测到的指标值及根据检测的指标值确定的其他指标值来判断压裂返排液是否适于配置压裂液；节省时间，分析效率较高。 【EN】The invention belongs to the technical field of fracturing flow-back fluid treatment, and discloses a deep treatment method of fracturing flow-back fluid for shale gas exploitation, wherein the deep treatment system comprises: the device comprises a video monitoring module, a parameter monitoring module, a main control module, a pretreatment module, an electrochemical oxidation treatment module, a precipitation filtering module, an evaporation concentration module, an analysis module, a power supply module and a display module. The parameters such as the fracturing flow-back fluid amount of each interval, the proportion of the fracturing fluid and the formation water in the fracturing flow-back fluid of each interval and the like can be directly measured and calculated through the parameter monitoring module, and the fracturing flow-back fluid profile of each interval can also be obtained; the judged fracturing condition is visual and accurate, quantitative analysis can be realized, the error is small, and an important guiding function is provided for the fracturing work of the same interval; meanwhile, whether the fracturing flow-back fluid is suitable for configuring the fracturing fluid is judged through an analysis module according to the detected index value and other index values determined according to the detected index value; time is saved, and the analysis efficiency is higher.

摘要：【中文】本发明公开了一种面向深度学习的医学影像标注方法及装置，其中，方法包括以下步骤：对输入的影像诊断报告、电子病历信息与医学影像进行预处理，生成包含医学影像与抽取出的相关诊断信息的数据；基于深度学习对医学影像进行预标注，其中，基于图像语义分割技术对影像进行分割，得到各个病变区域的边界范围，对影像实现像素级分割标注，并基于图像分类技术结合影像相关诊断信息对影像所属的疾病类型进行分类标注；将预标注后的影像及相关诊断信息通过界面展示，以接收交互式指令，供医生对预标注影像结果进行微调，并导出标注结果。该方法不仅提升了标注效率，同时保证了标注精度。 【EN】The invention discloses a medical image labeling method and device for deep learning, wherein the method comprises the following steps: preprocessing the input image diagnosis report, the electronic medical record information and the medical image to generate data containing the medical image and the extracted related diagnosis information; pre-labeling the medical image based on deep learning, wherein the image is segmented based on an image semantic segmentation technology to obtain the boundary range of each lesion area, pixel-level segmentation and labeling are realized on the image, and classification and labeling are performed on the disease type to which the image belongs based on an image classification technology and image related diagnosis information; and displaying the pre-marked image and the related diagnostic information through an interface to receive an interactive instruction, so that a doctor can finely adjust the result of the pre-marked image and export the marking result. The method not only improves the marking efficiency, but also ensures the marking precision.

摘要：【中文】本发明公开了一种多人协作图像标注质量控制的方法和装置，其中，方法包括：在标注包中按预设的比例投入金标准数据，以验证标注用户针对任一标注包的标注质量，通过验证的标注包数据暂定为合格，执行下一步骤，未通过的数据包将被重新打散，重新分配给用户进行标注；将一份图像分发给多位用户，收集多位用户对图像的标注结果，获取重复标签后，得到真实标签；以数据包或者用户为单位进行随机抽检，评价标注质量；将使用金标准推算的用户准确率反馈给用户，并将金标准中以及人工抽检出的错误数据及其对应的正确答案反馈给标注用户，以使标注用户接收再训练。该方法不仅可以保证标注质量，而且可以获取正确标注结果，简单易实现。 【EN】The invention discloses a method and a device for controlling quality of multi-person collaborative image annotation, wherein the method comprises the following steps: inputting gold standard data into the labeling packets according to a preset proportion to verify the labeling quality of a labeling user for any labeling packet, temporarily determining the qualified labeling packet data passing the verification to be qualified, executing the next step, scattering the data packets which do not pass the verification again, and redistributing the data packets to the user for labeling; distributing one image to a plurality of users, collecting the labeling results of the plurality of users to the image, and obtaining a real label after obtaining a repeated label; random sampling inspection is carried out by taking a data packet or a user as a unit, and the marking quality is evaluated; and feeding back the user accuracy calculated by using the gold standard to the user, and feeding back error data and corresponding correct answers in the gold standard and manually extracted and detected to the labeling user so as to enable the labeling user to receive retraining. The method can not only ensure the labeling quality, but also obtain the correct labeling result, and is simple and easy to implement.